Compare commits

...

68 Commits
3.4.0 ... 3.4.6

Author SHA1 Message Date
Alexey
8874396ba5 Merge pull request #739 from telemt/flow-test
Relays Tests Fixes
2026-04-24 15:51:47 +03:00
Alexey
033ebf5038 Relays Tests Fixes 2026-04-24 15:51:19 +03:00
Alexey
f7b918875c Close Errors Classification + TLS 1.2/1.3 Correctness in Fronting + Full ServerHello + ALPN in TLS Fetcher: merge pull request #738 from telemt/flow
Close Errors Classification + TLS 1.2/1.3 Correctness in Fronting + Full ServerHello + ALPN in TLS Fetcher
2026-04-24 15:48:39 +03:00
Alexey
8960fad8cd Сlassified Bad Connections and Handshake Failures in API
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-24 10:56:30 +03:00
Alexey
493f5c9680 ALPN in TLS Fetcher
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-23 22:22:05 +03:00
Alexey
67357310f7 TLS 1.2/1.3 Correctness + Full ServerHello + Rustfmt
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-23 21:29:18 +03:00
Alexey
8684378030 Human-readable Peer Close Classification 2026-04-21 15:46:18 +03:00
Alexey
db8d333ed6 Noisy-network peer Close Errors Classification 2026-04-21 15:35:11 +03:00
Alexey
30e73adaac Bump 2026-04-21 13:38:38 +03:00
Alexey
351f2c8458 Fairness Regression fixes + Unlimited mask_relay_max_bytes: merge pull request #726 from telemt/flow
Fairness Regression fixes + Unlimited mask_relay_max_bytes
2026-04-21 13:37:10 +03:00
Alexey
4ce6b14bd8 Rustfmt 2026-04-21 13:31:24 +03:00
Alexey
db114f09c3 Sync tests with code 2026-04-21 13:30:11 +03:00
Alexey
09310ff284 Unlimited mask_relay_max_bytes 2026-04-21 11:30:58 +03:00
Alexey
1e5b84c0ed Fairshare Disabled semantics fix 2026-04-21 11:21:58 +03:00
Alexey
926e3aa987 Fairness Regression fixes 2026-04-21 01:11:43 +03:00
Alexey
aace0129f8 Path for getProxyConfig/Secret + Active Ring and DRR Hardening + Weighted Fairness + 3-Leveled Pressure Model + Improve ME downstream retries + SNI handling: merge pull request #723 from telemt/flow
Path for getProxyConfig/Secret + Active Ring and DRR Hardening + Weighted Fairness + 3-Leveled Pressure Model + Improve ME downstream retries +  SNI handling
2026-04-19 19:12:10 +03:00
Alexey
2a7303c129 Bump 2026-04-19 19:10:19 +03:00
Alexey
9cb49bc024 Fix in Fairness tests 2026-04-19 19:03:45 +03:00
Alexey
8092283e8f Merge pull request #721 from lie-must-die/feat/unknown-sni-reject-handshake
Feat/unknown sni reject handshake
2026-04-19 14:19:22 +03:00
lie-must-die
132841da61 Update FAQ with SNI handling and metrics instructions
Added alternative configuration for unknown SNI handling and instructions for viewing metrics.
2026-04-19 12:50:26 +03:00
lie-must-die
372d288806 Добавить альтернативу для unknown_sni_action
Добавлена альтернатива для поведения telemt на неизвестный SNI.
2026-04-19 12:49:54 +03:00
lie-must-die
1c44d45fad Add 'reject_handshake' option to unknown_sni_action
Updated the `unknown_sni_action` parameter to include `reject_handshake` as a valid option. Expanded the description for `unknown_sni_action` to clarify its behavior.
2026-04-19 12:48:43 +03:00
lie-must-die
3a51a8d9aa Revise CONFIG_PARAMS.ru.md for clarity and detail
Updated descriptions and validation rules for various parameters in the Russian configuration documentation.
2026-04-19 12:47:26 +03:00
lie-must-die
dd27206104 Implement test for unknown SNI reject policy
Add test for unknown SNI rejection policy emitting TLS alert.
2026-04-19 12:44:39 +03:00
lie-must-die
f11c7880e6 Enhance unknown SNI action handling in handshake
Updated handling of unknown SNI actions in TLS handshake process. Added support for RejectHandshake action and adjusted delay application logic.
2026-04-19 12:43:54 +03:00
lie-must-die
5b07ffae7c Implement test for unknown_sni_action in ProxyConfig
Added test case for unknown_sni_action configuration.
2026-04-19 12:42:52 +03:00
lie-must-die
7bbed133ee Add RejectHandshake variant for TLS configuration
Added a new variant 'RejectHandshake' to handle TLS handshake rejection with a specific alert.
2026-04-19 12:40:10 +03:00
Alexey
f1bf95a7de Merge pull request #718 from astronaut808/fix/me-downstream-retry
Improve ME downstream retries for queued fairness backlog
2026-04-18 14:03:37 +03:00
Alexey
959a16af88 Merge pull request #716 from zarv1k/feature/configurable-proxy-confi-urls
feat: make URLS to obtain proxy_secret, getProxyConfig, getProxyConfgV6 files optionally configurable
2026-04-18 11:17:37 +03:00
Alexey
a54f9ba719 Merge branch 'flow' into feature/configurable-proxy-confi-urls 2026-04-18 11:16:38 +03:00
astronaut808
2d5cd9c8e1 Improve ME downstream retries for queued fairness backlog 2026-04-18 02:40:32 +05:00
Alexey
37b6f7b985 Weighted Fairness + 3-Leveled Pressure Model
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-18 00:37:04 +03:00
Alexey
50e9e5cf32 Active Ring and DRR Hardening
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-18 00:34:35 +03:00
Alexey
d72cfd6bc4 Merge branch 'flow' into feature/configurable-proxy-confi-urls 2026-04-17 19:44:46 +03:00
Alexey
1b25bada29 ServerHello fixes + Docker Health-Check + Conntrack Control for Docker: merge pull request #717 from telemt/flow
ServerHello fixes + Docker Health-Check + Conntrack Control for Docker
2026-04-17 19:43:59 +03:00
Dmitry Zarva
fa3566a9cb - fix: fmt issues 2026-04-17 16:20:16 +00:00
Alexey
bde30eaf05 Update emulator.rs 2026-04-17 19:20:06 +03:00
Alexey
b447f60a72 Rustfmt + Bump 2026-04-17 19:08:57 +03:00
Alexey
093faed0c2 Conntrack Control for Docker 2026-04-17 19:06:18 +03:00
Dmitry Zarva
4e59e52454 - fix: ru docs 2026-04-17 14:10:20 +00:00
Alexey
3ca3e8ff0e Docker Health-Check 2026-04-17 16:36:15 +03:00
Dmitry Zarva
7b9b46291d - fix: param name in ru docs 2026-04-17 13:19:29 +00:00
Dmitry Zarva
2a168b2600 feat: make URLS to obtain proxy_secret, getProxyConfig, getProxyConfigV6 files optionally configurable 2026-04-17 13:04:46 +00:00
Alexey
6e3b4a1ce5 ServerHello fixes 2026-04-17 15:11:36 +03:00
Alexey
cd0771eee4 Merge pull request #715 from telemt/flow
Fixes in TLS-F
2026-04-17 13:00:30 +03:00
Alexey
a858dd799e Bump 2026-04-17 12:43:41 +03:00
Alexey
947ef2beb7 Fixes in TLS-F 2026-04-17 12:38:22 +03:00
Alexey
376f9b42fb Traffic Control + Fairness + Evaluating hard-idle timeout + Improve FakeTLS server-flight fidelity + PROXY Protocol V2 UNKNOWN/LOCAL misuse fixes: merge pull request #714 from telemt/flow
Traffic Control + Fairness + Evaluating hard-idle timeout + Improve FakeTLS server-flight fidelity + PROXY Protocol V2 UNKNOWN/LOCAL misuse fixes
2026-04-17 11:54:18 +03:00
Alexey
191ca35076 Update scheduler.rs 2026-04-17 11:20:58 +03:00
Alexey
44485a545e Fixes for unused imports 2026-04-17 11:06:42 +03:00
Alexey
17a966b822 Rustfmt 2026-04-17 10:48:01 +03:00
Alexey
073eacbb37 PROXY Protocol V2 UNKNOWN/LOCAL misuse fixes for TLS-Fetcher by #713
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-17 10:43:49 +03:00
Alexey
5c99cd8eb7 Backpressure-driven Fairness
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-17 10:33:37 +03:00
Alexey
7494cb3092 Merge pull request #692 from ne4sp/patch-1
FIx XRAY_DOUBLE_HOP.md files.
2026-04-16 18:39:36 +03:00
Alexey
d100941426 Merge pull request #702 from astronaut808/security-tls-front-fidelity
Improve FakeTLS server-flight fidelity using captured TLS profiles
2026-04-16 16:13:23 +03:00
Alexey
d25aa5a1e9 Merge pull request #709 from groozchique/main
[docs] add hyperlinks to README
2026-04-16 16:12:48 +03:00
Nick Parfyonov
f1b7b9aa08 [docs] add hyperlinks to README 2026-04-16 09:40:55 +03:00
uncle Sam
3bff4fbfcd Merge branch 'main' into security-tls-front-fidelity 2026-04-15 19:45:35 +05:00
astronaut808
f5b5ea3bbf Improve FakeTLS server-flight fidelity and macOS portability 2026-04-15 19:35:09 +05:00
Alexey
f36f2eae24 Evaluating hard-idle timeout after read timeout
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-15 15:20:38 +03:00
Alexey
497ec6aa84 Small frames as idle activity
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-15 13:38:30 +03:00
Alexey
21ca1014ae Drafting Traffic Control
Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
2026-04-15 13:14:45 +03:00
Alexey
982bfd20b9 Merge pull request #707 from TWRoman/main
[docs] Updates in CONFIG_PARAMS based on lastest commits
2026-04-15 11:31:35 +03:00
Roman
0bcc3bf935 Update CONFIG_PARAMS.en.md 2026-04-15 10:29:37 +03:00
TWRoman
f7913721e2 Updates in CONFIG_PARAMS based on lastest commits 2026-04-15 10:25:31 +03:00
ne4sp
3f69b54f5d Update XRAY_DOUBLE_HOP.ru.md 2026-04-12 16:15:52 +03:00
ne4sp
62a90e05a0 Update XRAY_DOUBLE_HOP.en.md 2026-04-12 15:59:59 +03:00
ne4sp
1b3d2d8bc5 Update XRAY_DOUBLE_HOP.ru.md
При инициализации xray на сервере не запускался из-за длинного shortID.
2026-04-12 15:45:01 +03:00
75 changed files with 6442 additions and 568 deletions

206
Cargo.lock generated
View File

@@ -90,9 +90,9 @@ checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
[[package]]
name = "arc-swap"
version = "1.9.0"
version = "1.9.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a07d1f37ff60921c83bdfc7407723bdefe89b44b98a9b772f225c8f9d67141a6"
checksum = "6a3a1fd6f75306b68087b831f025c712524bcb19aad54e557b1129cfa0a2b207"
dependencies = [
"rustversion",
]
@@ -173,9 +173,9 @@ checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
[[package]]
name = "aws-lc-rs"
version = "1.16.2"
version = "1.16.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a054912289d18629dc78375ba2c3726a3afe3ff71b4edba9dedfca0e3446d1fc"
checksum = "0ec6fb3fe69024a75fa7e1bfb48aa6cf59706a101658ea01bfd33b2b248a038f"
dependencies = [
"aws-lc-sys",
"zeroize",
@@ -183,9 +183,9 @@ dependencies = [
[[package]]
name = "aws-lc-sys"
version = "0.39.1"
version = "0.40.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "83a25cf98105baa966497416dbd42565ce3a8cf8dbfd59803ec9ad46f3126399"
checksum = "f50037ee5e1e41e7b8f9d161680a725bd1626cb6f8c7e901f91f942850852fe7"
dependencies = [
"cc",
"cmake",
@@ -228,9 +228,9 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "bitflags"
version = "2.11.0"
version = "2.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "843867be96c8daad0d758b57df9392b6d8d271134fce549de6ce169ff98a92af"
checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
[[package]]
name = "blake3"
@@ -299,9 +299,9 @@ dependencies = [
[[package]]
name = "cc"
version = "1.2.58"
version = "1.2.60"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e1e928d4b69e3077709075a938a05ffbedfa53a84c8f766efbf8220bb1ff60e1"
checksum = "43c5703da9466b66a946814e1adf53ea2c90f10063b86290cc9eb67ce3478a20"
dependencies = [
"find-msvc-tools",
"jobserver",
@@ -346,7 +346,7 @@ checksum = "6f8d983286843e49675a4b7a2d174efe136dc93a18d69130dd18198a6c167601"
dependencies = [
"cfg-if",
"cpufeatures 0.3.0",
"rand_core 0.10.0",
"rand_core 0.10.1",
]
[[package]]
@@ -416,9 +416,9 @@ dependencies = [
[[package]]
name = "clap"
version = "4.6.0"
version = "4.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b193af5b67834b676abd72466a96c1024e6a6ad978a1f484bd90b85c94041351"
checksum = "1ddb117e43bbf7dacf0a4190fef4d345b9bad68dfc649cb349e7d17d28428e51"
dependencies = [
"clap_builder",
]
@@ -805,9 +805,9 @@ dependencies = [
[[package]]
name = "fastrand"
version = "2.3.0"
version = "2.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
checksum = "9f1f227452a390804cdb637b74a86990f2a7d7ba4b7d5693aac9b4dd6defd8d6"
[[package]]
name = "fiat-crypto"
@@ -997,7 +997,7 @@ dependencies = [
"cfg-if",
"libc",
"r-efi 6.0.0",
"rand_core 0.10.0",
"rand_core 0.10.1",
"wasip2",
"wasip3",
]
@@ -1068,6 +1068,12 @@ dependencies = [
"foldhash 0.2.0",
]
[[package]]
name = "hashbrown"
version = "0.17.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4f467dd6dccf739c208452f8014c75c18bb8301b050ad1cfb27153803edb0f51"
[[package]]
name = "heck"
version = "0.5.0"
@@ -1096,7 +1102,7 @@ dependencies = [
"idna",
"ipnet",
"once_cell",
"rand 0.9.2",
"rand 0.9.4",
"ring",
"thiserror 2.0.18",
"tinyvec",
@@ -1118,7 +1124,7 @@ dependencies = [
"moka",
"once_cell",
"parking_lot",
"rand 0.9.2",
"rand 0.9.4",
"resolv-conf",
"smallvec",
"thiserror 2.0.18",
@@ -1213,15 +1219,14 @@ dependencies = [
[[package]]
name = "hyper-rustls"
version = "0.27.7"
version = "0.27.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e3c93eb611681b207e1fe55d5a71ecf91572ec8a6705cdb6857f7d8d5242cf58"
checksum = "33ca68d021ef39cf6463ab54c1d0f5daf03377b70561305bb89a8f83aab66e0f"
dependencies = [
"http",
"hyper",
"hyper-util",
"rustls",
"rustls-pki-types",
"tokio",
"tokio-rustls",
"tower-service",
@@ -1385,12 +1390,12 @@ dependencies = [
[[package]]
name = "indexmap"
version = "2.13.0"
version = "2.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7714e70437a7dc3ac8eb7e6f8df75fd8eb422675fc7678aff7364301092b1017"
checksum = "d466e9454f08e4a911e14806c24e16fba1b4c121d1ea474396f396069cf949d9"
dependencies = [
"equivalent",
"hashbrown 0.16.1",
"hashbrown 0.17.0",
"serde",
"serde_core",
]
@@ -1401,7 +1406,7 @@ version = "0.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bd5b3eaf1a28b758ac0faa5a4254e8ab2705605496f1b1f3fbbc3988ad73d199"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
"inotify-sys",
"libc",
]
@@ -1534,9 +1539,9 @@ dependencies = [
[[package]]
name = "js-sys"
version = "0.3.94"
version = "0.3.95"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2e04e2ef80ce82e13552136fabeef8a5ed1f985a96805761cbb9a2c34e7664d9"
checksum = "2964e92d1d9dc3364cae4d718d93f227e3abb088e747d92e0395bfdedf1c12ca"
dependencies = [
"cfg-if",
"futures-util",
@@ -1578,9 +1583,9 @@ checksum = "09edd9e8b54e49e587e4f6295a7d29c3ea94d469cb40ab8ca70b288248a81db2"
[[package]]
name = "libc"
version = "0.2.184"
version = "0.2.185"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "48f5d2a454e16a5ea0f4ced81bd44e4cfc7bd3a507b61887c99fd3538b28e4af"
checksum = "52ff2c0fe9bc6cb6b14a0592c2ff4fa9ceb83eea9db979b0487cd054946a2b8f"
[[package]]
name = "linux-raw-sys"
@@ -1611,9 +1616,9 @@ checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
[[package]]
name = "lru"
version = "0.16.3"
version = "0.16.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a1dc47f592c06f33f8e3aea9591776ec7c9f9e4124778ff8a3c3b87159f7e593"
checksum = "7f66e8d5d03f609abc3a39e6f08e4164ebf1447a732906d39eb9b99b7919ef39"
dependencies = [
"hashbrown 0.16.1",
]
@@ -1705,7 +1710,7 @@ version = "0.31.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d6d0705320c1e6ba1d912b5e37cf18071b6c2e9b7fa8215a1e8a7651966f5d3"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
"cfg-if",
"cfg_aliases",
"libc",
@@ -1728,7 +1733,7 @@ version = "8.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4d3d07927151ff8575b7087f245456e549fea62edf0ec4e565a5ee50c8402bc3"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
"fsevent-sys",
"inotify",
"kqueue",
@@ -1746,7 +1751,7 @@ version = "2.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "42b8cfee0e339a0337359f3c88165702ac6e600dc01c0cc9579a92d62b08477a"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
]
[[package]]
@@ -2012,9 +2017,9 @@ checksum = "4b45fcc2344c680f5025fe57779faef368840d0bd1f42f216291f0dc4ace4744"
dependencies = [
"bit-set",
"bit-vec",
"bitflags 2.11.0",
"bitflags 2.11.1",
"num-traits",
"rand 0.9.2",
"rand 0.9.4",
"rand_chacha",
"rand_xorshift",
"regex-syntax",
@@ -2059,7 +2064,7 @@ dependencies = [
"bytes",
"getrandom 0.3.4",
"lru-slab",
"rand 0.9.2",
"rand 0.9.4",
"ring",
"rustc-hash",
"rustls",
@@ -2108,9 +2113,9 @@ checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
[[package]]
name = "rand"
version = "0.9.2"
version = "0.9.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
checksum = "44c5af06bb1b7d3216d91932aed5265164bf384dc89cd6ba05cf59a35f5f76ea"
dependencies = [
"rand_chacha",
"rand_core 0.9.5",
@@ -2118,13 +2123,13 @@ dependencies = [
[[package]]
name = "rand"
version = "0.10.0"
version = "0.10.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bc266eb313df6c5c09c1c7b1fbe2510961e5bcd3add930c1e31f7ed9da0feff8"
checksum = "d2e8e8bcc7961af1fdac401278c6a831614941f6164ee3bf4ce61b7edb162207"
dependencies = [
"chacha20 0.10.0",
"getrandom 0.4.2",
"rand_core 0.10.0",
"rand_core 0.10.1",
]
[[package]]
@@ -2157,9 +2162,9 @@ dependencies = [
[[package]]
name = "rand_core"
version = "0.10.0"
version = "0.10.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0c8d0fd677905edcbeedbf2edb6494d676f0e98d54d5cf9bda0b061cb8fb8aba"
checksum = "63b8176103e19a2643978565ca18b50549f6101881c443590420e4dc998a3c69"
[[package]]
name = "rand_xorshift"
@@ -2172,9 +2177,9 @@ dependencies = [
[[package]]
name = "rayon"
version = "1.11.0"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "368f01d005bf8fd9b1206fb6fa653e6c4a81ceb1466406b81792d87c5677a58f"
checksum = "fb39b166781f92d482534ef4b4b1b2568f42613b53e5b6c160e24cfbfa30926d"
dependencies = [
"either",
"rayon-core",
@@ -2196,7 +2201,7 @@ version = "0.5.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
]
[[package]]
@@ -2326,7 +2331,7 @@ version = "1.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
"errno",
"libc",
"linux-raw-sys",
@@ -2335,9 +2340,9 @@ dependencies = [
[[package]]
name = "rustls"
version = "0.23.37"
version = "0.23.38"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "758025cb5fccfd3bc2fd74708fd4682be41d99e5dff73c377c0646c6012c73a4"
checksum = "69f9466fb2c14ea04357e91413efb882e2a6d4a406e625449bc0a5d360d53a21"
dependencies = [
"aws-lc-rs",
"once_cell",
@@ -2399,9 +2404,9 @@ checksum = "f87165f0995f63a9fbeea62b64d10b4d9d8e78ec6d7d51fb2125fda7bb36788f"
[[package]]
name = "rustls-webpki"
version = "0.103.10"
version = "0.103.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df33b2b81ac578cabaf06b89b0631153a3f416b0a886e8a7a1707fb51abbd1ef"
checksum = "8279bb85272c9f10811ae6a6c547ff594d6a7f3c6c6b02ee9726d1d0dcfcdd06"
dependencies = [
"aws-lc-rs",
"ring",
@@ -2474,7 +2479,7 @@ version = "3.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b7f4bc775c73d9a02cde8bf7b2ec4c9d12743edf609006c7facc23998404cd1d"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
"core-foundation",
"core-foundation-sys",
"libc",
@@ -2493,9 +2498,9 @@ dependencies = [
[[package]]
name = "semver"
version = "1.0.27"
version = "1.0.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d767eb0aabc880b29956c35734170f26ed551a859dbd361d140cdbeca61ab1e2"
checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"
[[package]]
name = "sendfd"
@@ -2615,7 +2620,7 @@ dependencies = [
"notify",
"percent-encoding",
"pin-project",
"rand 0.9.2",
"rand 0.9.4",
"sealed",
"sendfd",
"serde",
@@ -2646,7 +2651,7 @@ dependencies = [
"chacha20poly1305",
"hkdf",
"md-5",
"rand 0.9.2",
"rand 0.9.4",
"ring-compat",
"sha1",
]
@@ -2741,6 +2746,12 @@ version = "2.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
[[package]]
name = "symlink"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a7973cce6668464ea31f176d85b13c7ab3bba2cb3b77a2ed26abd7801688010a"
[[package]]
name = "syn"
version = "2.0.117"
@@ -2780,7 +2791,7 @@ checksum = "7b2093cf4c8eb1e67749a6762251bc9cd836b6fc171623bd0a9d324d37af2417"
[[package]]
name = "telemt"
version = "3.4.0"
version = "3.4.6"
dependencies = [
"aes",
"anyhow",
@@ -2812,7 +2823,7 @@ dependencies = [
"num-traits",
"parking_lot",
"proptest",
"rand 0.10.0",
"rand 0.10.1",
"regex",
"reqwest",
"rustls",
@@ -2970,9 +2981,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
[[package]]
name = "tokio"
version = "1.50.0"
version = "1.52.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "27ad5e34374e03cfffefc301becb44e9dc3c17584f414349ebe29ed26661822d"
checksum = "b67dee974fe86fd92cc45b7a95fdd2f99a36a6d7b0d431a231178d3d670bbcc6"
dependencies = [
"bytes",
"libc",
@@ -2988,9 +2999,9 @@ dependencies = [
[[package]]
name = "tokio-macros"
version = "2.6.1"
version = "2.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c55a2eff8b69ce66c84f85e1da1c233edc36ceb85a2058d11b0d6a3c7e7569c"
checksum = "385a6cb71ab9ab790c5fe8d67f1645e6c450a7ce006a33de03daa956cf70a496"
dependencies = [
"proc-macro2",
"quote",
@@ -3123,7 +3134,7 @@ version = "0.6.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d4e6559d53cc268e5031cd8429d05415bc4cb4aefc4aa5d6cc35fbf5b924a1f8"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
"bytes",
"futures-util",
"http",
@@ -3160,11 +3171,12 @@ dependencies = [
[[package]]
name = "tracing-appender"
version = "0.2.4"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "786d480bce6247ab75f005b14ae1624ad978d3029d9113f0a22fa1ac773faeaf"
checksum = "050686193eb999b4bb3bc2acfa891a13da00f79734704c4b8b4ef1a10b368a3c"
dependencies = [
"crossbeam-channel",
"symlink",
"thiserror 2.0.18",
"time",
"tracing-subscriber",
@@ -3239,9 +3251,9 @@ checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
[[package]]
name = "typenum"
version = "1.19.0"
version = "1.20.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "562d481066bde0658276a35467c4af00bdc6ee726305698a55b86e61d7ad82bb"
checksum = "40ce102ab67701b8526c123c1bab5cbe42d7040ccfd0f64af1a385808d2f43de"
[[package]]
name = "unarray"
@@ -3297,9 +3309,9 @@ checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
[[package]]
name = "uuid"
version = "1.23.0"
version = "1.23.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5ac8b6f42ead25368cf5b098aeb3dc8a1a2c05a3eee8a9a1a68c640edbfc79d9"
checksum = "ddd74a9687298c6858e9b88ec8935ec45d22e8fd5e6394fa1bd4e99a87789c76"
dependencies = [
"getrandom 0.4.2",
"js-sys",
@@ -3354,11 +3366,11 @@ checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
[[package]]
name = "wasip2"
version = "1.0.2+wasi-0.2.9"
version = "1.0.3+wasi-0.2.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9517f9239f02c069db75e65f174b3da828fe5f5b945c4dd26bd25d89c03ebcf5"
checksum = "20064672db26d7cdc89c7798c48a0fdfac8213434a1186e5ef29fd560ae223d6"
dependencies = [
"wit-bindgen",
"wit-bindgen 0.57.1",
]
[[package]]
@@ -3367,14 +3379,14 @@ version = "0.4.0+wasi-0.3.0-rc-2026-01-06"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5428f8bf88ea5ddc08faddef2ac4a67e390b88186c703ce6dbd955e1c145aca5"
dependencies = [
"wit-bindgen",
"wit-bindgen 0.51.0",
]
[[package]]
name = "wasm-bindgen"
version = "0.2.117"
version = "0.2.118"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0551fc1bb415591e3372d0bc4780db7e587d84e2a7e79da121051c5c4b89d0b0"
checksum = "0bf938a0bacb0469e83c1e148908bd7d5a6010354cf4fb73279b7447422e3a89"
dependencies = [
"cfg-if",
"once_cell",
@@ -3385,9 +3397,9 @@ dependencies = [
[[package]]
name = "wasm-bindgen-futures"
version = "0.4.67"
version = "0.4.68"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "03623de6905b7206edd0a75f69f747f134b7f0a2323392d664448bf2d3c5d87e"
checksum = "f371d383f2fb139252e0bfac3b81b265689bf45b6874af544ffa4c975ac1ebf8"
dependencies = [
"js-sys",
"wasm-bindgen",
@@ -3395,9 +3407,9 @@ dependencies = [
[[package]]
name = "wasm-bindgen-macro"
version = "0.2.117"
version = "0.2.118"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7fbdf9a35adf44786aecd5ff89b4563a90325f9da0923236f6104e603c7e86be"
checksum = "eeff24f84126c0ec2db7a449f0c2ec963c6a49efe0698c4242929da037ca28ed"
dependencies = [
"quote",
"wasm-bindgen-macro-support",
@@ -3405,9 +3417,9 @@ dependencies = [
[[package]]
name = "wasm-bindgen-macro-support"
version = "0.2.117"
version = "0.2.118"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dca9693ef2bab6d4e6707234500350d8dad079eb508dca05530c85dc3a529ff2"
checksum = "9d08065faf983b2b80a79fd87d8254c409281cf7de75fc4b773019824196c904"
dependencies = [
"bumpalo",
"proc-macro2",
@@ -3418,9 +3430,9 @@ dependencies = [
[[package]]
name = "wasm-bindgen-shared"
version = "0.2.117"
version = "0.2.118"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39129a682a6d2d841b6c429d0c51e5cb0ed1a03829d8b3d1e69a011e62cb3d3b"
checksum = "5fd04d9e306f1907bd13c6361b5c6bfc7b3b3c095ed3f8a9246390f8dbdee129"
dependencies = [
"unicode-ident",
]
@@ -3453,7 +3465,7 @@ version = "0.244.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "47b807c72e1bac69382b3a6fb3dbe8ea4c0ed87ff5629b8685ae6b9a611028fe"
dependencies = [
"bitflags 2.11.0",
"bitflags 2.11.1",
"hashbrown 0.15.5",
"indexmap",
"semver",
@@ -3461,9 +3473,9 @@ dependencies = [
[[package]]
name = "web-sys"
version = "0.3.94"
version = "0.3.95"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cd70027e39b12f0849461e08ffc50b9cd7688d942c1c8e3c7b22273236b4dd0a"
checksum = "4f2dfbb17949fa2088e5d39408c48368947b86f7834484e87b73de55bc14d97d"
dependencies = [
"js-sys",
"wasm-bindgen",
@@ -3481,18 +3493,18 @@ dependencies = [
[[package]]
name = "webpki-root-certs"
version = "1.0.6"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "804f18a4ac2676ffb4e8b5b5fa9ae38af06df08162314f96a68d2a363e21a8ca"
checksum = "f31141ce3fc3e300ae89b78c0dd67f9708061d1d2eda54b8209346fd6be9a92c"
dependencies = [
"rustls-pki-types",
]
[[package]]
name = "webpki-roots"
version = "1.0.6"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "22cfaf3c063993ff62e73cb4311efde4db1efb31ab78a3e5c457939ad5cc0bed"
checksum = "52f5ee44c96cf55f1b349600768e3ece3a8f26010c05265ab73f945bb1a2eb9d"
dependencies = [
"rustls-pki-types",
]
@@ -3841,6 +3853,12 @@ dependencies = [
"wit-bindgen-rust-macro",
]
[[package]]
name = "wit-bindgen"
version = "0.57.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1ebf944e87a7c253233ad6766e082e3cd714b5d03812acc24c318f549614536e"
[[package]]
name = "wit-bindgen-core"
version = "0.51.0"
@@ -3890,7 +3908,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9d66ea20e9553b30172b5e831994e35fbde2d165325bec84fc43dbf6f4eb9cb2"
dependencies = [
"anyhow",
"bitflags 2.11.0",
"bitflags 2.11.1",
"indexmap",
"log",
"serde",
@@ -3922,9 +3940,9 @@ dependencies = [
[[package]]
name = "writeable"
version = "0.6.2"
version = "0.6.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9edde0db4769d2dc68579893f2306b26c6ecfbe0ef499b013d731b7b9247e0b9"
checksum = "1ffae5123b2d3fc086436f8834ae3ab053a283cfac8fe0a0b8eaae044768a4c4"
[[package]]
name = "x25519-dalek"

View File

@@ -1,6 +1,6 @@
[package]
name = "telemt"
version = "3.4.0"
version = "3.4.6"
edition = "2024"
[features]
@@ -98,4 +98,3 @@ harness = false
[profile.release]
lto = "fat"
codegen-units = 1

View File

@@ -77,6 +77,34 @@ COPY config.toml /app/config.toml
EXPOSE 443 9090 9091
HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 CMD ["/app/telemt", "healthcheck", "/app/config.toml", "--mode", "liveness"]
ENTRYPOINT ["/app/telemt"]
CMD ["config.toml"]
# ==========================
# Production Netfilter Profile
# ==========================
FROM debian:12-slim AS prod-netfilter
RUN set -eux; \
apt-get update; \
apt-get install -y --no-install-recommends \
ca-certificates \
conntrack \
nftables \
iptables; \
rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY --from=minimal /telemt /app/telemt
COPY config.toml /app/config.toml
EXPOSE 443 9090 9091
HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 CMD ["/app/telemt", "healthcheck", "/app/config.toml", "--mode", "liveness"]
ENTRYPOINT ["/app/telemt"]
CMD ["config.toml"]
@@ -94,5 +122,7 @@ USER nonroot:nonroot
EXPOSE 443 9090 9091
HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 CMD ["/app/telemt", "healthcheck", "/app/config.toml", "--mode", "liveness"]
ENTRYPOINT ["/app/telemt"]
CMD ["config.toml"]

View File

@@ -1,6 +1,6 @@
# Telemt - MTProxy on Rust + Tokio
![Latest Release](https://img.shields.io/github/v/release/telemt/telemt?color=neon) ![Stars](https://img.shields.io/github/stars/telemt/telemt?style=social) ![Forks](https://img.shields.io/github/forks/telemt/telemt?style=social) [![Telegram](https://img.shields.io/badge/Telegram-Chat-24a1de?logo=telegram&logoColor=24a1de)](https://t.me/telemtrs)
[![Latest Release](https://img.shields.io/github/v/release/telemt/telemt?color=neon)](https://github.com/telemt/telemt/releases/latest) [![Stars](https://img.shields.io/github/stars/telemt/telemt?style=social)](https://github.com/telemt/telemt/stargazers) [![Forks](https://img.shields.io/github/forks/telemt/telemt?style=social)](https://github.com/telemt/telemt/network/members) [![Telegram](https://img.shields.io/badge/Telegram-Chat-24a1de?logo=telegram&logoColor=24a1de)](https://t.me/telemtrs)
[🇷🇺 README на русском](https://github.com/telemt/telemt/blob/main/README.ru.md)

View File

@@ -1,6 +1,6 @@
# Telemt — MTProxy на Rust + Tokio
![Latest Release](https://img.shields.io/github/v/release/telemt/telemt?color=neon) ![Stars](https://img.shields.io/github/stars/telemt/telemt?style=social) ![Forks](https://img.shields.io/github/forks/telemt/telemt?style=social) [![Telegram](https://img.shields.io/badge/Telegram-Chat-24a1de?logo=telegram&logoColor=24a1de)](https://t.me/telemtrs)
[![Latest Release](https://img.shields.io/github/v/release/telemt/telemt?color=neon)](https://github.com/telemt/telemt/releases/latest) [![Stars](https://img.shields.io/github/stars/telemt/telemt?style=social)](https://github.com/telemt/telemt/stargazers) [![Forks](https://img.shields.io/github/forks/telemt/telemt?style=social)](https://github.com/telemt/telemt/network/members) [![Telegram](https://img.shields.io/badge/Telegram-Chat-24a1de?logo=telegram&logoColor=24a1de)](https://t.me/telemtrs)
***Решает проблемы раньше, чем другие узнают об их существовании***

View File

@@ -0,0 +1,10 @@
services:
telemt:
build:
context: .
target: prod-netfilter
network_mode: host
ports: []
cap_add:
- NET_BIND_SERVICE
- NET_ADMIN

View File

@@ -0,0 +1,8 @@
services:
telemt:
build:
context: .
target: prod-netfilter
cap_add:
- NET_BIND_SERVICE
- NET_ADMIN

View File

@@ -1,7 +1,9 @@
services:
telemt:
image: ghcr.io/telemt/telemt:latest
build: .
build:
context: .
target: prod
container_name: telemt
restart: unless-stopped
ports:
@@ -16,13 +18,18 @@ services:
- /etc/telemt:rw,mode=1777,size=4m
environment:
- RUST_LOG=info
healthcheck:
test: [ "CMD", "/app/telemt", "healthcheck", "/etc/telemt/config.toml", "--mode", "liveness" ]
interval: 30s
timeout: 5s
retries: 3
start_period: 20s
# Uncomment this line if you want to use host network for IPv6, but bridge is default and usually better
# network_mode: host
cap_drop:
- ALL
cap_add:
- NET_BIND_SERVICE
- NET_ADMIN
read_only: true
security_opt:
- no-new-privileges:true

View File

@@ -0,0 +1,225 @@
# TLS Front Profile Fidelity
## Overview
This document describes how Telemt reuses captured TLS behavior in the FakeTLS server flight and how to validate the result on a real deployment.
When TLS front emulation is enabled, Telemt can capture useful server-side TLS behavior from the selected origin and reuse that behavior in the emulated success path. The goal is not to reproduce the origin byte-for-byte, but to reduce stable synthetic traits and make the emitted server flight structurally closer to the captured profile.
## Why this change exists
The project already captures useful server-side TLS behavior in the TLS front fetch path:
- `change_cipher_spec_count`
- `app_data_record_sizes`
- `ticket_record_sizes`
Before this change, the emulator used only part of that information. This left a gap between captured origin behavior and emitted FakeTLS server flight.
## What is implemented
- The emulator now replays the observed `ChangeCipherSpec` count from the fetched behavior profile.
- The emulator now replays observed ticket-like tail ApplicationData record sizes when raw or merged TLS profile data is available.
- The emulator now preserves more of the profiled encrypted-flight structure instead of collapsing it into a smaller synthetic shape.
- The emulator still falls back to the previous synthetic behavior when the cached profile does not contain raw TLS behavior information.
- Operator-configured `tls_new_session_tickets` still works as an additive fallback when the profile does not provide enough tail records.
## Practical benefit
- Reduced distinguishability between profiled origin TLS behavior and emulated TLS behavior.
- Lower chance of stable server-flight fingerprints caused by fixed CCS count or synthetic-only tail record sizes.
- Better reuse of already captured TLS profile data without changing MTProto logic, KDF routing, or transport architecture.
## Limitations
This mechanism does not aim to make Telemt byte-identical to the origin server.
It also does not change:
- MTProto business logic;
- KDF routing behavior;
- the overall transport architecture.
The practical goal is narrower:
- reuse more captured profile data;
- reduce fixed synthetic behavior in the server flight;
- preserve a valid FakeTLS success path while changing the emitted shape on the wire.
## Validation targets
- Correct count of emulated `ChangeCipherSpec` records.
- Correct replay of observed ticket-tail record sizes.
- No regression in existing ALPN and payload-placement behavior.
## How to validate the result
Recommended validation consists of two layers:
- focused unit and security tests for CCS-count replay and ticket-tail replay;
- real packet-capture comparison for a selected origin and a successful FakeTLS session.
When testing on the network, the expected result is:
- a valid FakeTLS and MTProto success path is preserved;
- the early encrypted server flight changes shape when richer profile data is available;
- the change is visible on the wire without changing MTProto logic or transport architecture.
This validation is intended to show better reuse of captured TLS profile data.
It is not intended to prove byte-level equivalence with the real origin server.
## How to test on a real deployment
The strongest practical validation is a side-by-side trace comparison between:
- a real TLS origin server used as `mask_host`;
- a Telemt FakeTLS success-path connection for the same SNI;
- optional captures from different Telemt builds or configurations.
The purpose of the comparison is to inspect the shape of the server flight:
- record order;
- count of `ChangeCipherSpec` records;
- count and grouping of early encrypted `ApplicationData` records;
- lengths of tail or continuation `ApplicationData` records.
## Recommended environment
Use a Linux host or Docker container for the cleanest reproduction.
Recommended setup:
1. One Telemt instance.
2. One real HTTPS origin as `mask_host`.
3. One Telegram client configured with an `ee` proxy link for the Telemt instance.
4. `tcpdump` or Wireshark available for capture analysis.
## Step-by-step test procedure
### 1. Prepare the origin
1. Choose a real HTTPS origin.
2. Set both `censorship.tls_domain` and `censorship.mask_host` to that hostname.
3. Confirm that a direct TLS request works:
```bash
openssl s_client -connect ORIGIN_IP:443 -servername YOUR_DOMAIN </dev/null
```
### 2. Configure Telemt
Use a configuration that enables:
- `censorship.mask = true`
- `censorship.tls_emulation = true`
- `censorship.mask_host`
- `censorship.mask_port`
Recommended for cleaner testing:
- keep `censorship.tls_new_session_tickets = 0`, so the result depends primarily on fetched profile data rather than operator-forced synthetic tail records;
- keep `censorship.tls_fetch.strict_route = true`, if cleaner provenance for captured profile data is important.
### 3. Refresh TLS profile data
1. Start Telemt.
2. Let it fetch TLS front profile data for the configured domain.
3. If `tls_front_dir` is persisted, confirm that the TLS front cache is populated.
Persisted cache artifacts are useful, but they are not required if packet captures already demonstrate the runtime result.
### 4. Capture a direct-origin trace
From a separate client host, connect directly to the origin:
```bash
openssl s_client -connect ORIGIN_IP:443 -servername YOUR_DOMAIN </dev/null
```
Capture with:
```bash
sudo tcpdump -i any -w origin-direct.pcap host ORIGIN_IP and port 443
```
### 5. Capture a Telemt FakeTLS success-path trace
Now connect to Telemt with a real Telegram client through an `ee` proxy link that targets the Telemt instance.
`openssl s_client` is useful for direct-origin capture and fallback sanity checks, but it does not exercise the successful FakeTLS and MTProto path.
Capture with:
```bash
sudo tcpdump -i any -w telemt-emulated.pcap host TELEMT_IP and port 443
```
### 6. Decode TLS record structure
Use `tshark` to print record-level structure:
```bash
tshark -r origin-direct.pcap -Y "tls.record" -T fields \
-e frame.number \
-e ip.src \
-e ip.dst \
-e tls.record.content_type \
-e tls.record.length
```
```bash
tshark -r telemt-emulated.pcap -Y "tls.record" -T fields \
-e frame.number \
-e ip.src \
-e ip.dst \
-e tls.record.content_type \
-e tls.record.length
```
Focus on the server flight after ClientHello:
- `22` = Handshake
- `20` = ChangeCipherSpec
- `23` = ApplicationData
### 7. Build a comparison table
A compact table like the following is usually enough:
| Path | CCS count | AppData count in first encrypted flight | Tail AppData lengths |
| --- | --- | --- | --- |
| Origin | `N` | `M` | `[a, b, ...]` |
| Telemt build A | `...` | `...` | `...` |
| Telemt build B | `...` | `...` | `...` |
The comparison should make it easy to see that:
- the FakeTLS success path remains valid;
- the early encrypted server flight changes when richer profile data is reused;
- the result is backed by packet evidence.
## Example capture set
One practical example of this workflow uses:
- `origin-direct-nginx.pcap`
- `telemt-ee-before-nginx.pcap`
- `telemt-ee-after-nginx.pcap`
Practical notes:
- `origin` was captured as a direct TLS 1.2 connection to `nginx.org`;
- `before` and `after` were captured on the Telemt FakeTLS success path with a real Telegram client;
- the first server-side FakeTLS response remains valid in both cases;
- the early encrypted server-flight segmentation differs between `before` and `after`, which is consistent with better reuse of captured profile data;
- this kind of result shows a wire-visible effect without breaking the success path, but it does not claim full indistinguishability from the origin.
## Stronger validation
For broader confidence, repeat the same comparison on:
1. one CDN-backed origin;
2. one regular nginx origin;
3. one origin with a multi-record encrypted flight and visible ticket-like tails.
If the same directional improvement appears across all three, confidence in the result will be much higher than for a single-origin example.

View File

@@ -0,0 +1,225 @@
# Fidelity TLS Front Profile
## Обзор
Этот документ описывает, как Telemt переиспользует захваченное TLS-поведение в FakeTLS server flight и как проверять результат на реальной инсталляции.
Когда включена TLS front emulation, Telemt может собирать полезное серверное TLS-поведение выбранного origin и использовать его в emulated success path. Цель здесь не в побайтном копировании origin, а в уменьшении устойчивых synthetic признаков и в том, чтобы emitted server flight был структурно ближе к захваченному profile.
## Зачем нужно это изменение
Проект уже умеет собирать полезное серверное TLS-поведение в пути TLS front fetch:
- `change_cipher_spec_count`
- `app_data_record_sizes`
- `ticket_record_sizes`
До этого изменения эмулятор использовал только часть этой информации. Из-за этого оставался разрыв между захваченным поведением origin и тем FakeTLS server flight, который реально уходил на провод.
## Что реализовано
- Эмулятор теперь воспроизводит наблюдаемое значение `ChangeCipherSpec` из полученного `behavior_profile`.
- Эмулятор теперь воспроизводит наблюдаемые размеры ticket-like tail ApplicationData records, когда доступны raw или merged TLS profile data.
- Эмулятор теперь сохраняет больше структуры профилированного encrypted flight, а не схлопывает его в более маленькую synthetic форму.
- Для профилей без raw TLS behavior по-прежнему сохраняется прежний synthetic fallback.
- Операторский `tls_new_session_tickets` по-прежнему работает как дополнительный fallback, если профиль не даёт достаточного количества tail records.
## Практическая польза
- Снижается различимость между профилированным origin TLS-поведением и эмулируемым TLS-поведением.
- Уменьшается шанс устойчивых server-flight fingerprint, вызванных фиксированным CCS count или полностью synthetic tail record sizes.
- Уже собранные TLS profile data используются лучше, без изменения MTProto logic, KDF routing или transport architecture.
## Ограничения
Этот механизм не ставит целью сделать Telemt побайтно идентичным origin server.
Он также не меняет:
- MTProto business logic;
- поведение KDF routing;
- общую transport architecture.
Практическая цель уже:
- использовать больше уже собранных profile data;
- уменьшить fixed synthetic behavior в server flight;
- сохранить валидный FakeTLS success path, одновременно меняя форму emitted traffic на проводе.
## Цели валидации
- Корректное количество эмулируемых `ChangeCipherSpec` records.
- Корректное воспроизведение наблюдаемых ticket-tail record sizes.
- Отсутствие регрессии в существующем ALPN и payload-placement behavior.
## Как проверять результат
Рекомендуемая валидация состоит из двух слоёв:
- focused unit и security tests для CCS-count replay и ticket-tail replay;
- сравнение реальных packet capture для выбранного origin и успешной FakeTLS session.
При проверке на сети ожидаемый результат такой:
- валидный FakeTLS и MTProto success path сохраняется;
- форма раннего encrypted server flight меняется, когда доступно более богатое profile data;
- изменение видно на проводе без изменения MTProto logic и transport architecture.
Такая проверка нужна для подтверждения того, что уже собранные TLS profile data используются лучше.
Она не предназначена для доказательства побайтной эквивалентности с реальным origin server.
## Как проверить на реальной инсталляции
Самая сильная практическая проверка — side-by-side trace comparison между:
- реальным TLS origin server, используемым как `mask_host`;
- Telemt FakeTLS success-path connection для того же SNI;
- при необходимости capture от разных Telemt builds или configurations.
Смысл сравнения состоит в том, чтобы посмотреть на форму server flight:
- порядок records;
- количество `ChangeCipherSpec` records;
- количество и группировку ранних encrypted `ApplicationData` records;
- размеры tail или continuation `ApplicationData` records.
## Рекомендуемое окружение
Для самой чистой проверки лучше использовать Linux host или Docker container.
Рекомендуемый setup:
1. Один экземпляр Telemt.
2. Один реальный HTTPS origin как `mask_host`.
3. Один Telegram client, настроенный на `ee` proxy link для Telemt instance.
4. `tcpdump` или Wireshark для анализа capture.
## Пошаговая процедура проверки
### 1. Подготовить origin
1. Выберите реальный HTTPS origin.
2. Установите и `censorship.tls_domain`, и `censorship.mask_host` в hostname этого origin.
3. Убедитесь, что прямой TLS request работает:
```bash
openssl s_client -connect ORIGIN_IP:443 -servername YOUR_DOMAIN </dev/null
```
### 2. Настроить Telemt
Используйте config, где включены:
- `censorship.mask = true`
- `censorship.tls_emulation = true`
- `censorship.mask_host`
- `censorship.mask_port`
Для более чистой проверки рекомендуется:
- держать `censorship.tls_new_session_tickets = 0`, чтобы результат в первую очередь зависел от fetched profile data, а не от операторских synthetic tail records;
- держать `censorship.tls_fetch.strict_route = true`, если важна более чистая provenance для captured profile data.
### 3. Обновить TLS profile data
1. Запустите Telemt.
2. Дайте ему получить TLS front profile data для выбранного домена.
3. Если `tls_front_dir` хранится persistently, убедитесь, что TLS front cache заполнен.
Persisted cache artifacts полезны, но не обязательны, если packet capture уже показывают runtime result.
### 4. Снять direct-origin trace
С отдельной клиентской машины подключитесь напрямую к origin:
```bash
openssl s_client -connect ORIGIN_IP:443 -servername YOUR_DOMAIN </dev/null
```
Capture:
```bash
sudo tcpdump -i any -w origin-direct.pcap host ORIGIN_IP and port 443
```
### 5. Снять Telemt FakeTLS success-path trace
Теперь подключитесь к Telemt через реальный Telegram client с `ee` proxy link, который указывает на Telemt instance.
`openssl s_client` полезен для direct-origin capture и для fallback sanity checks, но он не проходит успешный FakeTLS и MTProto path.
Capture:
```bash
sudo tcpdump -i any -w telemt-emulated.pcap host TELEMT_IP and port 443
```
### 6. Декодировать структуру TLS records
Используйте `tshark`, чтобы вывести record-level structure:
```bash
tshark -r origin-direct.pcap -Y "tls.record" -T fields \
-e frame.number \
-e ip.src \
-e ip.dst \
-e tls.record.content_type \
-e tls.record.length
```
```bash
tshark -r telemt-emulated.pcap -Y "tls.record" -T fields \
-e frame.number \
-e ip.src \
-e ip.dst \
-e tls.record.content_type \
-e tls.record.length
```
Смотрите на server flight после ClientHello:
- `22` = Handshake
- `20` = ChangeCipherSpec
- `23` = ApplicationData
### 7. Собрать сравнительную таблицу
Обычно достаточно короткой таблицы такого вида:
| Path | CCS count | AppData count in first encrypted flight | Tail AppData lengths |
| --- | --- | --- | --- |
| Origin | `N` | `M` | `[a, b, ...]` |
| Telemt build A | `...` | `...` | `...` |
| Telemt build B | `...` | `...` | `...` |
По такой таблице должно быть легко увидеть, что:
- FakeTLS success path остаётся валидным;
- ранний encrypted server flight меняется, когда переиспользуется более богатое profile data;
- результат подтверждён packet evidence.
## Пример набора capture
Один практический пример такой проверки использует:
- `origin-direct-nginx.pcap`
- `telemt-ee-before-nginx.pcap`
- `telemt-ee-after-nginx.pcap`
Практические замечания:
- `origin` снимался как прямое TLS 1.2 connection к `nginx.org`;
- `before` и `after` снимались на Telemt FakeTLS success path с реальным Telegram client;
- первый server-side FakeTLS response остаётся валидным в обоих случаях;
- сегментация раннего encrypted server flight отличается между `before` и `after`, что согласуется с лучшим использованием captured profile data;
- такой результат показывает заметный эффект на проводе без поломки success path, но не заявляет полной неотличимости от origin.
## Более сильная валидация
Для более широкой проверки повторите ту же процедуру ещё на:
1. одном CDN-backed origin;
2. одном regular nginx origin;
3. одном origin с multi-record encrypted flight и заметными ticket-like tails.
Если одно и то же направление улучшения повторится на всех трёх, уверенность в результате будет значительно выше, чем для одного origin example.

View File

@@ -255,13 +255,22 @@ This document lists all configuration keys accepted by `config.toml`.
```
## proxy_secret_path
- **Constraints / validation**: `String`. When omitted, the default path is `"proxy-secret"`. Empty values are accepted by TOML/serde but will likely fail at runtime (invalid file path).
- **Description**: Path to Telegram infrastructure `proxy-secret` cache file used by ME handshake/RPC auth. Telemt always tries a fresh download from `https://core.telegram.org/getProxySecret` first, caches it to this path on success, and falls back to reading the cached file (any age) on download failure.
- **Description**: Path to Telegram infrastructure `proxy-secret` cache file used by ME handshake/RPC auth. Telemt always tries a fresh download from `https://core.telegram.org/getProxySecret` first (unless `proxy_secret_url` is set) , caches it to this path on success, and falls back to reading the cached file (any age) on download failure.
- **Example**:
```toml
[general]
proxy_secret_path = "proxy-secret"
```
## proxy_secret_url
- **Constraints / validation**: `String`. When omitted, the `"https://core.telegram.org/getProxySecret"` is used.
- **Description**: Optional URL to obtain `proxy-secret` file used by ME handshake/RPC auth. Telemt always tries a fresh download from this URL first (with fallback to `https://core.telegram.org/getProxySecret` if absent).
- **Example**:
```toml
[general]
proxy_secret_url = "https://core.telegram.org/getProxySecret"
```
## proxy_config_v4_cache_path
- **Constraints / validation**: `String`. When set, must not be empty/whitespace-only.
- **Description**: Optional disk cache path for raw `getProxyConfig` (IPv4) snapshot. At startup Telemt tries to fetch a fresh snapshot first; on fetch failure or empty snapshot it falls back to this cache file when present and non-empty.
@@ -271,6 +280,15 @@ This document lists all configuration keys accepted by `config.toml`.
[general]
proxy_config_v4_cache_path = "cache/proxy-config-v4.txt"
```
## proxy_config_v4_url
- **Constraints / validation**: `String`. When omitted, the `"https://core.telegram.org/getProxyConfig"` is used.
- **Description**: Optional URL to obtain raw `getProxyConfig` (IPv4). Telemt always tries a fresh download from this URL first (with fallback to `https://core.telegram.org/getProxyConfig` if absent).
- **Example**:
```toml
[general]
proxy_config_v4_url = "https://core.telegram.org/getProxyConfig"
```
## proxy_config_v6_cache_path
- **Constraints / validation**: `String`. When set, must not be empty/whitespace-only.
- **Description**: Optional disk cache path for raw `getProxyConfigV6` (IPv6) snapshot. At startup Telemt tries to fetch a fresh snapshot first; on fetch failure or empty snapshot it falls back to this cache file when present and non-empty.
@@ -280,6 +298,15 @@ This document lists all configuration keys accepted by `config.toml`.
[general]
proxy_config_v6_cache_path = "cache/proxy-config-v6.txt"
```
## proxy_config_v6_url
- **Constraints / validation**: `String`. When omitted, the `"https://core.telegram.org/getProxyConfigV6"` is used.
- **Description**: Optional URL to obtain raw `getProxyConfigV6` (IPv6). Telemt always tries a fresh download from this URL first (with fallback to `https://core.telegram.org/getProxyConfigV6` if absent).
- **Example**:
```toml
[general]
proxy_config_v6_url = "https://core.telegram.org/getProxyConfigV6"
```
## ad_tag
- **Constraints / validation**: `String` (optional). When set, must be exactly 32 hex characters; invalid values are disabled during config load.
- **Description**: Global fallback sponsored-channel `ad_tag` (used when user has no override in `access.user_ad_tags`). An all-zero tag is accepted but has no effect (and is warned about) until replaced with a real tag from `@MTProxybot`.
@@ -2268,40 +2295,39 @@ Note: This section also accepts the legacy alias `[server.admin_api]` (same sche
| Key | Type | Default |
| --- | ---- | ------- |
| [`tls_domain`](#cfg-censorship-tls_domain) | `String` | `"petrovich.ru"` |
| [`tls_domains`](#cfg-censorship-tls_domains) | `String[]` | `[]` |
| [`unknown_sni_action`](#cfg-censorship-unknown_sni_action) | `"drop"`, `"mask"`, `"accept"` | `"drop"` |
| [`tls_fetch_scope`](#cfg-censorship-tls_fetch_scope) | `String` | `""` |
| [`tls_fetch`](#cfg-censorship-tls_fetch) | `Table` | built-in defaults |
| [`mask`](#cfg-censorship-mask) | `bool` | `true` |
| [`mask_host`](#cfg-censorship-mask_host) | `String` | — |
| [`mask_port`](#cfg-censorship-mask_port) | `u16` | `443` |
| [`mask_unix_sock`](#cfg-censorship-mask_unix_sock) | `String` | — |
| [`fake_cert_len`](#cfg-censorship-fake_cert_len) | `usize` | `2048` |
| [`tls_emulation`](#cfg-censorship-tls_emulation) | `bool` | `true` |
| [`tls_front_dir`](#cfg-censorship-tls_front_dir) | `String` | `"tlsfront"` |
| [`server_hello_delay_min_ms`](#cfg-censorship-server_hello_delay_min_ms) | `u64` | `0` |
| [`server_hello_delay_max_ms`](#cfg-censorship-server_hello_delay_max_ms) | `u64` | `0` |
| [`tls_new_session_tickets`](#cfg-censorship-tls_new_session_tickets) | `u8` | `0` |
| [`tls_full_cert_ttl_secs`](#cfg-censorship-tls_full_cert_ttl_secs) | `u64` | `90` |
| [`alpn_enforce`](#cfg-censorship-alpn_enforce) | `bool` | `true` |
| [`mask_proxy_protocol`](#cfg-censorship-mask_proxy_protocol) | `u8` | `0` |
| [`mask_shape_hardening`](#cfg-censorship-mask_shape_hardening) | `bool` | `true` |
| [`mask_shape_hardening_aggressive_mode`](#cfg-censorship-mask_shape_hardening_aggressive_mode) | `bool` | `false` |
| [`mask_shape_bucket_floor_bytes`](#cfg-censorship-mask_shape_bucket_floor_bytes) | `usize` | `512` |
| [`mask_shape_bucket_cap_bytes`](#cfg-censorship-mask_shape_bucket_cap_bytes) | `usize` | `4096` |
| [`mask_shape_above_cap_blur`](#cfg-censorship-mask_shape_above_cap_blur) | `bool` | `false` |
| [`mask_shape_above_cap_blur_max_bytes`](#cfg-censorship-mask_shape_above_cap_blur_max_bytes) | `usize` | `512` |
| [`mask_relay_max_bytes`](#cfg-censorship-mask_relay_max_bytes) | `usize` | `5242880` |
| [`mask_relay_timeout_ms`](#cfg-censorship-mask_relay_timeout_ms) | `u64` | `60_000` |
| [`mask_relay_idle_timeout_ms`](#cfg-censorship-mask_relay_idle_timeout_ms) | `u64` | `5_000` |
| [`mask_classifier_prefetch_timeout_ms`](#cfg-censorship-mask_classifier_prefetch_timeout_ms) | `u64` | `5` |
| [`mask_timing_normalization_enabled`](#cfg-censorship-mask_timing_normalization_enabled) | `bool` | `false` |
| [`mask_timing_normalization_floor_ms`](#cfg-censorship-mask_timing_normalization_floor_ms) | `u64` | `0` |
| [`mask_timing_normalization_ceiling_ms`](#cfg-censorship-mask_timing_normalization_ceiling_ms) | `u64` | `0` |
| [`tls_domain`](#tls_domain) | `String` | `"petrovich.ru"` |
| [`tls_domains`](#tls_domains) | `String[]` | `[]` |
| [`unknown_sni_action`](#unknown_sni_action) | `"drop"`, `"mask"`, `"accept"`, `"reject_handshake"` | `"drop"` |
| [`tls_fetch_scope`](#tls_fetch_scope) | `String` | `""` |
| [`tls_fetch`](#tls_fetch) | `Table` | built-in defaults |
| [`mask`](#mask) | `bool` | `true` |
| [`mask_host`](#mask_host) | `String` | — |
| [`mask_port`](#mask_port) | `u16` | `443` |
| [`mask_unix_sock`](#mask_unix_sock) | `String` | — |
| [`fake_cert_len`](#fake_cert_len) | `usize` | `2048` |
| [`tls_emulation`](#tls_emulation) | `bool` | `true` |
| [`tls_front_dir`](#tls_front_dir) | `String` | `"tlsfront"` |
| [`server_hello_delay_min_ms`](#server_hello_delay_min_ms) | `u64` | `0` |
| [`server_hello_delay_max_ms`](#server_hello_delay_max_ms) | `u64` | `0` |
| [`tls_new_session_tickets`](#tls_new_session_tickets) | `u8` | `0` |
| [`tls_full_cert_ttl_secs`](#tls_full_cert_ttl_secs) | `u64` | `90` |
| [`alpn_enforce`](#alpn_enforce) | `bool` | `true` |
| [`mask_proxy_protocol`](#mask_proxy_protocol) | `u8` | `0` |
| [`mask_shape_hardening`](#mask_shape_hardening) | `bool` | `true` |
| [`mask_shape_hardening_aggressive_mode`](#mask_shape_hardening_aggressive_mode) | `bool` | `false` |
| [`mask_shape_bucket_floor_bytes`](#mask_shape_bucket_floor_bytes) | `usize` | `512` |
| [`mask_shape_bucket_cap_bytes`](#mask_shape_bucket_cap_bytes) | `usize` | `4096` |
| [`mask_shape_above_cap_blur`](#mask_shape_above_cap_blur) | `bool` | `false` |
| [`mask_shape_above_cap_blur_max_bytes`](#mask_shape_above_cap_blur_max_bytes) | `usize` | `512` |
| [`mask_relay_max_bytes`](#mask_relay_max_bytes) | `usize` | `5242880` |
| [`mask_relay_timeout_ms`](#mask_relay_timeout_ms) | `u64` | `60_000` |
| [`mask_relay_idle_timeout_ms`](#mask_relay_idle_timeout_ms) | `u64` | `5_000` |
| [`mask_classifier_prefetch_timeout_ms`](#mask_classifier_prefetch_timeout_ms) | `u64` | `5` |
| [`mask_timing_normalization_enabled`](#mask_timing_normalization_enabled) | `bool` | `false` |
| [`mask_timing_normalization_floor_ms`](#mask_timing_normalization_floor_ms) | `u64` | `0` |
| [`mask_timing_normalization_ceiling_ms`](#mask_timing_normalization_ceiling_ms) | `u64` | `0` |
## "cfg-censorship-tls_domain"
- `tls_domain`
## tls_domain
- **Constraints / validation**: Must be a non-empty domain name. Must not contain spaces or `/`.
- **Description**: Primary domain used for Fake-TLS masking / fronting profile and as the default SNI domain presented to clients.
This value becomes part of generated `ee` links, and changing it invalidates previously generated links.
@@ -2322,13 +2348,17 @@ Note: This section also accepts the legacy alias `[server.admin_api]` (same sche
tls_domains = ["example.net", "example.org"]
```
## unknown_sni_action
- **Constraints / validation**: `"drop"`, `"mask"` or `"accept"`.
- **Constraints / validation**: `"drop"`, `"mask"`, `"accept"` or `"reject_handshake"`.
- **Description**: Action for TLS ClientHello with unknown / non-configured SNI.
- `drop` — close the connection without any response (silent FIN after `server_hello_delay` is applied). Timing-indistinguishable from the Success branch, but wire-quieter than what a real web server would do.
- `mask` — transparently proxy the connection to `mask_host:mask_port` (TLS fronting). The client receives a real ServerHello from the backend with its real certificate. Maximum camouflage, but opens an outbound connection for every misdirected request.
- `accept` — pretend the SNI is valid and continue on the auth path. Weakens active-probing resistance; only meaningful in narrow scenarios.
- `reject_handshake` — emit a fatal TLS `unrecognized_name` alert (RFC 6066, AlertDescription = 112) and close the connection. Identical on the wire to a modern nginx with `ssl_reject_handshake on;` on its default vhost: looks like an ordinary HTTPS server that simply does not host the requested name. Recommended when the goal is maximal parity with a stock web server rather than TLS fronting. `server_hello_delay` is intentionally **not** applied to this branch, so the alert is emitted "instantly" the way a reference nginx would.
- **Example**:
```toml
[censorship]
unknown_sni_action = "drop"
unknown_sni_action = "reject_handshake"
```
## tls_fetch_scope
- **Constraints / validation**: `String`. Value is trimmed during load; whitespace-only becomes empty.
@@ -2542,8 +2572,7 @@ Note: This section also accepts the legacy alias `[server.admin_api]` (same sche
[censorship]
mask_relay_max_bytes = 5242880
```
## "cfg-censorship-mask_relay_timeout_ms"
- `mask_relay_timeout_ms`
## mask_relay_timeout_ms
- **Constraints / validation**: Should be `>= mask_relay_idle_timeout_ms`.
- **Description**: Wall-clock cap for the full masking relay on non-MTProto fallback paths. Raise when the mask target is a long-lived service (e.g. WebSocket). Default: 60 000 ms (1 minute).
- **Example**:
@@ -2552,8 +2581,7 @@ Note: This section also accepts the legacy alias `[server.admin_api]` (same sche
[censorship]
mask_relay_timeout_ms = 60000
```
## "cfg-censorship-mask_relay_idle_timeout_ms"
- `mask_relay_idle_timeout_ms`
## mask_relay_idle_timeout_ms
- **Constraints / validation**: Should be `<= mask_relay_timeout_ms`.
- **Description**: Per-read idle timeout on masking relay and drain paths. Limits resource consumption by slow-loris attacks and port scanners. A read call stalling beyond this value is treated as an abandoned connection. Default: 5 000 ms (5 s).
- **Example**:
@@ -2562,8 +2590,7 @@ Note: This section also accepts the legacy alias `[server.admin_api]` (same sche
[censorship]
mask_relay_idle_timeout_ms = 5000
```
## "cfg-censorship-mask_classifier_prefetch_timeout_ms"
- `mask_classifier_prefetch_timeout_ms`
## mask_classifier_prefetch_timeout_ms
- **Constraints / validation**: Must be within `[5, 50]` (milliseconds).
- **Description**: Timeout budget (ms) for extending fragmented initial classifier window on masking fallback.
- **Example**:
@@ -3087,5 +3114,3 @@ If your backend or network is very bandwidth-constrained, reduce cap first. If p
username = "alice"
password = "secret"
```

View File

@@ -255,13 +255,22 @@
```
## proxy_secret_path
- **Ограничения / валидация**: `String`. Если этот параметр не указан, используется путь по умолчанию — «proxy-secret». Пустые значения принимаются TOML/serde, но во время выполнения произойдет ошибка (invalid file path).
- **Описание**: Путь к файлу кэша `proxy-secret` инфраструктуры Telegram, используемому ME-handshake/аутентификацией RPC. Telemt всегда сначала пытается выполнить новую загрузку с https://core.telegram.org/getProxySecret, в случае успеха кэширует ее по этому пути и возвращается к чтению кэшированного файла в случае сбоя загрузки.
- **Описание**: Путь к файлу кэша `proxy-secret` инфраструктуры Telegram, используемому ME-handshake/аутентификацией RPC. Telemt всегда сначала пытается выполнить новую загрузку с https://core.telegram.org/getProxySecret (если не установлен `proxy_secret_url`), в случае успеха кэширует ее по этому пути и возвращается к чтению кэшированного файла в случае сбоя загрузки.
- **Пример**:
```toml
[general]
proxy_secret_path = "proxy-secret"
```
## proxy_secret_url
- **Ограничения / валидация**: `String`. Если не указан, используется `"https://core.telegram.org/getProxySecret"`.
- **Описание**: Необязательный URL для получения файла `proxy-secret` используемого ME-handshake/аутентификацией RPC. Telemt всегда сначала пытается выполнить новую загрузку с этого URL (если не задан, используется https://core.telegram.org/getProxySecret).
- **Пример**:
```toml
[general]
proxy_secret_url = "https://core.telegram.org/getProxySecret"
```
## proxy_config_v4_cache_path
- **Ограничения / валидация**: `String`. Если используется, значение не должно быть пустым или содержать только пробелы.
- **Описание**: Необязательный путь к кэшу для необработанного (raw) снимка getProxyConfig (IPv4). При запуске Telemt сначала пытается получить свежий снимок; в случае сбоя выборки или пустого снимка он возвращается к этому файлу кэша, если он присутствует и не пуст.
@@ -271,6 +280,15 @@
[general]
proxy_config_v4_cache_path = "cache/proxy-config-v4.txt"
```
## proxy_config_v4_url
- **Ограничения / валидация**: `String`. Если не указан, используется `"https://core.telegram.org/getProxyConfig"`.
- **Описание**: Необязательный URL для получения `getProxyConfig` (IPv4). Telemt при всегда пытается выполнить новую загрузку с этого URL (и если не задан, использует `https://core.telegram.org/getProxyConfig`).
- **Example**:
```toml
[general]
proxy_config_v4_url = "https://core.telegram.org/getProxyConfig"
```
## proxy_config_v6_cache_path
- **Ограничения / валидация**: `String`. Если используется, значение не должно быть пустым или содержать только пробелы.
- **Описание**: Необязательный путь к кэшу для необработанного (raw) снимка getProxyConfigV6 (IPv6). При запуске Telemt сначала пытается получить свежий снимок; в случае сбоя выборки или пустого снимка он возвращается к этому файлу кэша, если он присутствует и не пуст.
@@ -280,6 +298,15 @@
[general]
proxy_config_v6_cache_path = "cache/proxy-config-v6.txt"
```
## proxy_config_v6_url
- **Ограничения / валидация**: `String`. Если не указан, используется `"https://core.telegram.org/getProxyConfigV6"`.
- **Описание**: Необязательный URL для получения `getProxyConfigV6` (IPv6). Telemt при всегда пытается выполнить новую загрузку с этого URL (и если не задан, использует `https://core.telegram.org/getProxyConfigV6`).
- **Example**:
```toml
[general]
proxy_config_v6_url = "https://core.telegram.org/getProxyConfigV6"
```
## ad_tag
- **Ограничения / валидация**: `String` (необязательный параметр). Если используется, значение должно быть ровно 32 символа в шестнадцатеричной системе; недопустимые значения отключаются во время загрузки конфигурации.
- **Описание**: Глобальный резервный спонсируемый канал `ad_tag` (используется, когда у пользователя нет переопределения в `access.user_ad_tags`). Тег со всеми нулями принимается, но не имеет никакого эффекта, пока не будет заменен реальным тегом от `@MTProxybot`.
@@ -2197,7 +2224,7 @@
```
## relay_client_idle_soft_secs
- **Ограничения / валидация**: Должно быть `> 0`; Должно быть меньше или равно `relay_client_idle_hard_secs`.
- **Описание**: Мягкий порог простоя (в секундах) для неактивности uplink клиента в промежуточном узле. При достижении этого порога сессия помечается как кандидат на простой и может быть удалена в зависимости от политики.
- **Описание**: Мягкий порог простоя (в секундах) для неактивности uplink клиента в промежуточном узле. При достижении этого порога сессия помечается как кандидат на простой и может быть удалена в зависимости от политики.
- **Пример**:
```toml
@@ -2276,7 +2303,7 @@
| --- | ---- | ------- |
| [`tls_domain`](#tls_domain) | `String` | `"petrovich.ru"` |
| [`tls_domains`](#tls_domains) | `String[]` | `[]` |
| [`unknown_sni_action`](#unknown_sni_action) | `"drop"`, `"mask"`, `"accept"` | `"drop"` |
| [`unknown_sni_action`](#unknown_sni_action) | `"drop"`, `"mask"`, `"accept"`, `"reject_handshake"` | `"drop"` |
| [`tls_fetch_scope`](#tls_fetch_scope) | `String` | `""` |
| [`tls_fetch`](#tls_fetch) | `Table` | built-in defaults |
| [`mask`](#mask) | `bool` | `true` |
@@ -2299,6 +2326,8 @@
| [`mask_shape_above_cap_blur`](#mask_shape_above_cap_blur) | `bool` | `false` |
| [`mask_shape_above_cap_blur_max_bytes`](#mask_shape_above_cap_blur_max_bytes) | `usize` | `512` |
| [`mask_relay_max_bytes`](#mask_relay_max_bytes) | `usize` | `5242880` |
| [`mask_relay_timeout_ms`](mask_relay_timeout_ms) | `u64` | `60_000` |
| [`mask_relay_idle_timeout_ms`](mask_relay_idle_timeout_ms) | `u64` | `5_000` |
| [`mask_classifier_prefetch_timeout_ms`](#mask_classifier_prefetch_timeout_ms) | `u64` | `5` |
| [`mask_timing_normalization_enabled`](#mask_timing_normalization_enabled) | `bool` | `false` |
| [`mask_timing_normalization_floor_ms`](#mask_timing_normalization_floor_ms) | `u64` | `0` |
@@ -2324,13 +2353,17 @@
tls_domains = ["example.net", "example.org"]
```
## unknown_sni_action
- **Ограничения / валидация**: `"drop"`, `"mask"` или `"accept"`.
- **Ограничения / валидация**: `"drop"`, `"mask"`, `"accept"` или `"reject_handshake"`.
- **Описание**: Действие для TLS ClientHello с неизвестным/ненастроенным SNI.
- `drop` — закрыть соединение без ответа (молчаливый FIN после применения `server_hello_delay`). Поведение, неотличимое по таймингу от Success-ветки, но более «тихое», чем у обычного веб-сервера.
- `mask` — прозрачно проксировать соединение на `mask_host:mask_port` (TLS-fronting). Клиент получает настоящий ServerHello от реального бэкенда с его сертификатом. Максимальный камуфляж, но порождает исходящее соединение на каждый чужой запрос.
- `accept` — притвориться, что SNI валиден, и продолжить auth-путь. Снижает защиту от активного пробинга; осмысленно только в узких сценариях.
- `reject_handshake` — отправить фатальный TLS-alert `unrecognized_name` (RFC 6066, AlertDescription = 112) и закрыть соединение. Поведение, идентичное современному nginx с `ssl_reject_handshake on;` на дефолтном vhost'е: на wire-уровне выглядит как обычный HTTPS-сервер, у которого просто нет такого домена. Рекомендуется, если цель — максимальная похожесть на стоковый веб-сервер, а не tls-fronting. `server_hello_delay` на эту ветку не применяется, чтобы alert улетал «мгновенно», как у эталонного nginx.
- **Пример**:
```toml
[censorship]
unknown_sni_action = "drop"
unknown_sni_action = "reject_handshake"
```
## tls_fetch_scope
- **Ограничения / валидация**: `String`. Значение обрезается во время загрузки; значение, состоящее только из пробелов, становится пустым.
@@ -2544,6 +2577,26 @@
[censorship]
mask_relay_max_bytes = 5242880
```
## mask_relay_timeout_ms
- **Constraints / validation**: Должно быть больше или равно `mask_relay_idle_timeout_ms`.
- **Description**: Жёсткий лимит по реальному времени (wall-clock) для полного маскирующего проксирования на fallback-путях без MTProto. Увеличивайте значение, если целевой сервис маскирования является долгоживущим (например, WebSocket-соединение). Значение по умолчанию: 60 000 мс (1 минута).
- **Example**:
```toml
[censorship]
mask_relay_timeout_ms = 60000
```
## mask_relay_idle_timeout_ms
- **Constraints / validation**: Должно быть меньше или равно `mask_relay_timeout_ms`.
- **Description**: Тайм-аут простоя на каждую операцию чтения (per-read idle timeout) в маскирующем прокси и drain-пайплайнах. Ограничивает потребление ресурсов при атаках типа slow-loris и сканировании портов. Если операция чтения блокируется дольше заданного времени, соединение считается заброшенным и закрывается. Значение по умолчанию: 5 000 мс (5 с).
- **Example**:
```toml
[censorship]
mask_relay_idle_timeout_ms = 5000
```
## mask_classifier_prefetch_timeout_ms
- **Ограничения / валидация**: Должно быть в пределах `[5, 50]` (миллисекунд).
- **Описание**: Лимит времени ожидания (в миллисекундах) для расширения первых входящих данных в режиме fallback-маскировки.
@@ -3068,5 +3121,3 @@
username = "alice"
password = "secret"
```

View File

@@ -210,6 +210,13 @@ If you need to allow connections with any domains (ignoring SNI mismatches), add
unknown_sni_action = "mask"
```
Alternatively, if you want telemt to behave like a vanilla nginx with `ssl_reject_handshake on;` on unknown SNI (emit a TLS `unrecognized_name` alert and close the connection), use:
```toml
[censorship]
unknown_sni_action = "reject_handshake"
```
This does not recover stale clients, but it makes port 443 wire-indistinguishable from a stock web server that simply does not host the requested vhost.
### How to view metrics
1. Open the configuration file: `nano /etc/telemt/telemt.toml`.

View File

@@ -227,6 +227,13 @@ curl -s http://127.0.0.1:9091/v1/users | jq
unknown_sni_action = "mask"
```
Альтернатива: если вы хотите, чтобы telemt на неизвестный SNI вёл себя как обычный nginx с `ssl_reject_handshake on;` (отдавал TLS-alert `unrecognized_name` и закрывал соединение), используйте:
```toml
[censorship]
unknown_sni_action = "reject_handshake"
```
Это не пропускает старых клиентов, но делает поведение на 443-м порту неотличимым от стокового веб-сервера, у которого просто нет такого виртуального хоста.
## Как посмотреть метрики
1. Откройте файл конфигурации: `nano /etc/telemt/telemt.toml`.

View File

@@ -37,13 +37,13 @@ xray x25519
```
3. **Short ID (Reality identifier):**
```bash
openssl rand -hex 16
# Save the output (e.g.: 0123456789abcdef0123456789abcdef) — this is <SHORT_ID>
openssl rand -hex 8
# Save the output (e.g.: abc123def456) — this is <SHORT_ID>
```
4. **Random Path (for xhttp):**
```bash
openssl rand -hex 8
# Save the output (e.g., abc123def456) to replace <YOUR_RANDOM_PATH> in configs
openssl rand -hex 16
# Save the output (e.g., 0123456789abcdef0123456789abcdef) to replace <YOUR_RANDOM_PATH> in configs
```
---

View File

@@ -37,13 +37,13 @@ xray x25519
```
3. **Short ID (идентификатор Reality):**
```bash
openssl rand -hex 16
# Сохраните вывод (например: 0123456789abcdef0123456789abcdef) — это <SHORT_ID>
openssl rand -hex 8
# Сохраните вывод (например: abc123def456) — это <SHORT_ID>
```
4. **Random Path (путь для xhttp):**
```bash
openssl rand -hex 8
# Сохраните вывод (например, abc123def456), чтобы заменить <YOUR_RANDOM_PATH> в конфигах
openssl rand -hex 16
# Сохраните вывод (например, 0123456789abcdef0123456789abcdef), чтобы заменить <YOUR_RANDOM_PATH> в конфигах
```
---

View File

@@ -41,8 +41,8 @@ use config_store::{current_revision, load_config_from_disk, parse_if_match};
use events::ApiEventStore;
use http_utils::{error_response, read_json, read_optional_json, success_response};
use model::{
ApiFailure, CreateUserRequest, DeleteUserResponse, HealthData, PatchUserRequest,
RotateSecretRequest, SummaryData, UserActiveIps,
ApiFailure, ClassCount, CreateUserRequest, DeleteUserResponse, HealthData, HealthReadyData,
PatchUserRequest, RotateSecretRequest, SummaryData, UserActiveIps,
};
use runtime_edge::{
EdgeConnectionsCacheEntry, build_runtime_connections_summary_data,
@@ -275,6 +275,33 @@ async fn handle(
};
Ok(success_response(StatusCode::OK, data, revision))
}
("GET", "/v1/health/ready") => {
let revision = current_revision(&shared.config_path).await?;
let admission_open = shared.runtime_state.admission_open.load(Ordering::Relaxed);
let upstream_health = shared.upstream_manager.api_health_summary().await;
let ready = admission_open && upstream_health.healthy_total > 0;
let reason = if ready {
None
} else if !admission_open {
Some("admission_closed")
} else {
Some("no_healthy_upstreams")
};
let data = HealthReadyData {
ready,
status: if ready { "ready" } else { "not_ready" },
reason,
admission_open,
healthy_upstreams: upstream_health.healthy_total,
total_upstreams: upstream_health.configured_total,
};
let status_code = if ready {
StatusCode::OK
} else {
StatusCode::SERVICE_UNAVAILABLE
};
Ok(success_response(status_code, data, revision))
}
("GET", "/v1/system/info") => {
let revision = current_revision(&shared.config_path).await?;
let data = build_system_info_data(shared.as_ref(), cfg.as_ref(), &revision);
@@ -307,10 +334,24 @@ async fn handle(
}
("GET", "/v1/stats/summary") => {
let revision = current_revision(&shared.config_path).await?;
let connections_bad_by_class = shared
.stats
.get_connects_bad_class_counts()
.into_iter()
.map(|(class, total)| ClassCount { class, total })
.collect();
let handshake_failures_by_class = shared
.stats
.get_handshake_failure_class_counts()
.into_iter()
.map(|(class, total)| ClassCount { class, total })
.collect();
let data = SummaryData {
uptime_seconds: shared.stats.uptime_secs(),
connections_total: shared.stats.get_connects_all(),
connections_bad_total: shared.stats.get_connects_bad(),
connections_bad_by_class,
handshake_failures_by_class,
handshake_timeouts_total: shared.stats.get_handshake_timeouts(),
configured_users: cfg.access.users.len(),
};

View File

@@ -60,11 +60,30 @@ pub(super) struct HealthData {
pub(super) read_only: bool,
}
#[derive(Serialize)]
pub(super) struct HealthReadyData {
pub(super) ready: bool,
pub(super) status: &'static str,
#[serde(skip_serializing_if = "Option::is_none")]
pub(super) reason: Option<&'static str>,
pub(super) admission_open: bool,
pub(super) healthy_upstreams: usize,
pub(super) total_upstreams: usize,
}
#[derive(Serialize, Clone)]
pub(super) struct ClassCount {
pub(super) class: String,
pub(super) total: u64,
}
#[derive(Serialize)]
pub(super) struct SummaryData {
pub(super) uptime_seconds: f64,
pub(super) connections_total: u64,
pub(super) connections_bad_total: u64,
pub(super) connections_bad_by_class: Vec<ClassCount>,
pub(super) handshake_failures_by_class: Vec<ClassCount>,
pub(super) handshake_timeouts_total: u64,
pub(super) configured_users: usize,
}
@@ -80,6 +99,8 @@ pub(super) struct ZeroCoreData {
pub(super) uptime_seconds: f64,
pub(super) connections_total: u64,
pub(super) connections_bad_total: u64,
pub(super) connections_bad_by_class: Vec<ClassCount>,
pub(super) handshake_failures_by_class: Vec<ClassCount>,
pub(super) handshake_timeouts_total: u64,
pub(super) accept_permit_timeout_total: u64,
pub(super) configured_users: usize,

View File

@@ -7,8 +7,8 @@ use crate::transport::upstream::IpPreference;
use super::ApiShared;
use super::model::{
DcEndpointWriters, DcStatus, DcStatusData, MeWriterStatus, MeWritersData, MeWritersSummary,
MinimalAllData, MinimalAllPayload, MinimalDcPathData, MinimalMeRuntimeData,
ClassCount, DcEndpointWriters, DcStatus, DcStatusData, MeWriterStatus, MeWritersData,
MeWritersSummary, MinimalAllData, MinimalAllPayload, MinimalDcPathData, MinimalMeRuntimeData,
MinimalQuarantineData, UpstreamDcStatus, UpstreamStatus, UpstreamSummaryData, UpstreamsData,
ZeroAllData, ZeroCodeCount, ZeroCoreData, ZeroDesyncData, ZeroMiddleProxyData, ZeroPoolData,
ZeroUpstreamData,
@@ -26,6 +26,16 @@ pub(crate) struct MinimalCacheEntry {
pub(super) fn build_zero_all_data(stats: &Stats, configured_users: usize) -> ZeroAllData {
let telemetry = stats.telemetry_policy();
let bad_connection_classes = stats
.get_connects_bad_class_counts()
.into_iter()
.map(|(class, total)| ClassCount { class, total })
.collect();
let handshake_failure_classes = stats
.get_handshake_failure_class_counts()
.into_iter()
.map(|(class, total)| ClassCount { class, total })
.collect();
let handshake_error_codes = stats
.get_me_handshake_error_code_counts()
.into_iter()
@@ -38,6 +48,8 @@ pub(super) fn build_zero_all_data(stats: &Stats, configured_users: usize) -> Zer
uptime_seconds: stats.uptime_secs(),
connections_total: stats.get_connects_all(),
connections_bad_total: stats.get_connects_bad(),
connections_bad_by_class: bad_connection_classes,
handshake_failures_by_class: handshake_failure_classes,
handshake_timeouts_total: stats.get_handshake_timeouts(),
accept_permit_timeout_total: stats.get_accept_permit_timeout_total(),
configured_users,

View File

@@ -6,12 +6,15 @@
//! - `reload [--pid-file PATH]` - Reload configuration (SIGHUP)
//! - `status [--pid-file PATH]` - Check daemon status
//! - `run [OPTIONS] [config.toml]` - Run in foreground (default behavior)
//! - `healthcheck [OPTIONS] [config.toml]` - Run control-plane health probe
use rand::RngExt;
use std::fs;
use std::path::{Path, PathBuf};
use std::process::Command;
use crate::healthcheck::{self, HealthcheckMode};
#[cfg(unix)]
use crate::daemon::{self, DEFAULT_PID_FILE, DaemonOptions};
@@ -28,6 +31,8 @@ pub enum Subcommand {
Reload,
/// Check daemon status (`status` subcommand).
Status,
/// Run health probe and exit with status code.
Healthcheck,
/// Fire-and-forget setup (`--init`).
Init,
}
@@ -38,6 +43,8 @@ pub struct ParsedCommand {
pub subcommand: Subcommand,
pub pid_file: PathBuf,
pub config_path: String,
pub healthcheck_mode: HealthcheckMode,
pub healthcheck_mode_invalid: Option<String>,
#[cfg(unix)]
pub daemon_opts: DaemonOptions,
pub init_opts: Option<InitOptions>,
@@ -52,6 +59,8 @@ impl Default for ParsedCommand {
#[cfg(not(unix))]
pid_file: PathBuf::from("/var/run/telemt.pid"),
config_path: "config.toml".to_string(),
healthcheck_mode: HealthcheckMode::Liveness,
healthcheck_mode_invalid: None,
#[cfg(unix)]
daemon_opts: DaemonOptions::default(),
init_opts: None,
@@ -91,6 +100,9 @@ pub fn parse_command(args: &[String]) -> ParsedCommand {
"status" => {
cmd.subcommand = Subcommand::Status;
}
"healthcheck" => {
cmd.subcommand = Subcommand::Healthcheck;
}
"run" => {
cmd.subcommand = Subcommand::Run;
#[cfg(unix)]
@@ -113,7 +125,35 @@ pub fn parse_command(args: &[String]) -> ParsedCommand {
while i < args.len() {
match args[i].as_str() {
// Skip subcommand names
"start" | "stop" | "reload" | "status" | "run" => {}
"start" | "stop" | "reload" | "status" | "run" | "healthcheck" => {}
"--mode" => {
i += 1;
if i < args.len() {
match HealthcheckMode::from_cli_arg(&args[i]) {
Some(mode) => {
cmd.healthcheck_mode = mode;
cmd.healthcheck_mode_invalid = None;
}
None => {
cmd.healthcheck_mode_invalid = Some(args[i].clone());
}
}
} else {
cmd.healthcheck_mode_invalid = Some(String::new());
}
}
s if s.starts_with("--mode=") => {
let raw = s.trim_start_matches("--mode=");
match HealthcheckMode::from_cli_arg(raw) {
Some(mode) => {
cmd.healthcheck_mode = mode;
cmd.healthcheck_mode_invalid = None;
}
None => {
cmd.healthcheck_mode_invalid = Some(raw.to_string());
}
}
}
// PID file option (for stop/reload/status)
"--pid-file" => {
i += 1;
@@ -152,6 +192,20 @@ pub fn execute_subcommand(cmd: &ParsedCommand) -> Option<i32> {
Subcommand::Stop => Some(cmd_stop(&cmd.pid_file)),
Subcommand::Reload => Some(cmd_reload(&cmd.pid_file)),
Subcommand::Status => Some(cmd_status(&cmd.pid_file)),
Subcommand::Healthcheck => {
if let Some(invalid_mode) = cmd.healthcheck_mode_invalid.as_ref() {
if invalid_mode.is_empty() {
eprintln!("[telemt] Missing value for --mode (supported: liveness, ready)");
} else {
eprintln!(
"[telemt] Invalid --mode value '{invalid_mode}' (supported: liveness, ready)"
);
}
Some(2)
} else {
Some(healthcheck::run(&cmd.config_path, cmd.healthcheck_mode))
}
}
Subcommand::Init => {
if let Some(opts) = cmd.init_opts.clone() {
match run_init(opts) {
@@ -177,6 +231,20 @@ pub fn execute_subcommand(cmd: &ParsedCommand) -> Option<i32> {
eprintln!("[telemt] Subcommand not supported on this platform");
Some(1)
}
Subcommand::Healthcheck => {
if let Some(invalid_mode) = cmd.healthcheck_mode_invalid.as_ref() {
if invalid_mode.is_empty() {
eprintln!("[telemt] Missing value for --mode (supported: liveness, ready)");
} else {
eprintln!(
"[telemt] Invalid --mode value '{invalid_mode}' (supported: liveness, ready)"
);
}
Some(2)
} else {
Some(healthcheck::run(&cmd.config_path, cmd.healthcheck_mode))
}
}
Subcommand::Init => {
if let Some(opts) = cmd.init_opts.clone() {
match run_init(opts) {
@@ -621,6 +689,7 @@ tls_domain = "{domain}"
mask = true
mask_port = 443
fake_cert_len = 2048
serverhello_compact = false
tls_full_cert_ttl_secs = 90
[access]

View File

@@ -21,6 +21,8 @@ const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_ACTIVE_WRITERS_PER_CORE: u16 = 64;
const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_WARM_WRITERS_PER_CORE: u16 = 64;
const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_ACTIVE_WRITERS_GLOBAL: u32 = 256;
const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_WARM_WRITERS_GLOBAL: u32 = 256;
const DEFAULT_ME_ROUTE_BACKPRESSURE_ENABLED: bool = false;
const DEFAULT_ME_ROUTE_FAIRSHARE_ENABLED: bool = false;
const DEFAULT_ME_WRITER_CMD_CHANNEL_CAPACITY: usize = 4096;
const DEFAULT_ME_ROUTE_CHANNEL_CAPACITY: usize = 768;
const DEFAULT_ME_C2ME_CHANNEL_CAPACITY: usize = 1024;
@@ -529,6 +531,14 @@ pub(crate) fn default_me_route_backpressure_base_timeout_ms() -> u64 {
25
}
pub(crate) fn default_me_route_backpressure_enabled() -> bool {
DEFAULT_ME_ROUTE_BACKPRESSURE_ENABLED
}
pub(crate) fn default_me_route_fairshare_enabled() -> bool {
DEFAULT_ME_ROUTE_FAIRSHARE_ENABLED
}
pub(crate) fn default_me_route_backpressure_high_timeout_ms() -> u64 {
120
}
@@ -565,6 +575,10 @@ pub(crate) fn default_tls_new_session_tickets() -> u8 {
0
}
pub(crate) fn default_serverhello_compact() -> bool {
false
}
pub(crate) fn default_tls_full_cert_ttl_secs() -> u64 {
90
}

View File

@@ -86,6 +86,8 @@ pub struct HotFields {
pub telemetry_user_enabled: bool,
pub telemetry_me_level: MeTelemetryLevel,
pub me_socks_kdf_policy: MeSocksKdfPolicy,
pub me_route_backpressure_enabled: bool,
pub me_route_fairshare_enabled: bool,
pub me_floor_mode: MeFloorMode,
pub me_adaptive_floor_idle_secs: u64,
pub me_adaptive_floor_min_writers_single_endpoint: u8,
@@ -121,6 +123,9 @@ pub struct HotFields {
pub user_max_tcp_conns_global_each: usize,
pub user_expirations: std::collections::HashMap<String, chrono::DateTime<chrono::Utc>>,
pub user_data_quota: std::collections::HashMap<String, u64>,
pub user_rate_limits: std::collections::HashMap<String, crate::config::RateLimitBps>,
pub cidr_rate_limits:
std::collections::HashMap<ipnetwork::IpNetwork, crate::config::RateLimitBps>,
pub user_max_unique_ips: std::collections::HashMap<String, usize>,
pub user_max_unique_ips_global_each: usize,
pub user_max_unique_ips_mode: crate::config::UserMaxUniqueIpsMode,
@@ -184,6 +189,8 @@ impl HotFields {
telemetry_user_enabled: cfg.general.telemetry.user_enabled,
telemetry_me_level: cfg.general.telemetry.me_level,
me_socks_kdf_policy: cfg.general.me_socks_kdf_policy,
me_route_backpressure_enabled: cfg.general.me_route_backpressure_enabled,
me_route_fairshare_enabled: cfg.general.me_route_fairshare_enabled,
me_floor_mode: cfg.general.me_floor_mode,
me_adaptive_floor_idle_secs: cfg.general.me_adaptive_floor_idle_secs,
me_adaptive_floor_min_writers_single_endpoint: cfg
@@ -245,6 +252,8 @@ impl HotFields {
user_max_tcp_conns_global_each: cfg.access.user_max_tcp_conns_global_each,
user_expirations: cfg.access.user_expirations.clone(),
user_data_quota: cfg.access.user_data_quota.clone(),
user_rate_limits: cfg.access.user_rate_limits.clone(),
cidr_rate_limits: cfg.access.cidr_rate_limits.clone(),
user_max_unique_ips: cfg.access.user_max_unique_ips.clone(),
user_max_unique_ips_global_each: cfg.access.user_max_unique_ips_global_each,
user_max_unique_ips_mode: cfg.access.user_max_unique_ips_mode,
@@ -524,6 +533,8 @@ fn overlay_hot_fields(old: &ProxyConfig, new: &ProxyConfig) -> ProxyConfig {
new.general.me_route_backpressure_high_timeout_ms;
cfg.general.me_route_backpressure_high_watermark_pct =
new.general.me_route_backpressure_high_watermark_pct;
cfg.general.me_route_backpressure_enabled = new.general.me_route_backpressure_enabled;
cfg.general.me_route_fairshare_enabled = new.general.me_route_fairshare_enabled;
cfg.general.me_reader_route_data_wait_ms = new.general.me_reader_route_data_wait_ms;
cfg.general.me_d2c_flush_batch_max_frames = new.general.me_d2c_flush_batch_max_frames;
cfg.general.me_d2c_flush_batch_max_bytes = new.general.me_d2c_flush_batch_max_bytes;
@@ -545,6 +556,8 @@ fn overlay_hot_fields(old: &ProxyConfig, new: &ProxyConfig) -> ProxyConfig {
cfg.access.user_max_tcp_conns_global_each = new.access.user_max_tcp_conns_global_each;
cfg.access.user_expirations = new.access.user_expirations.clone();
cfg.access.user_data_quota = new.access.user_data_quota.clone();
cfg.access.user_rate_limits = new.access.user_rate_limits.clone();
cfg.access.cidr_rate_limits = new.access.cidr_rate_limits.clone();
cfg.access.user_max_unique_ips = new.access.user_max_unique_ips.clone();
cfg.access.user_max_unique_ips_global_each = new.access.user_max_unique_ips_global_each;
cfg.access.user_max_unique_ips_mode = new.access.user_max_unique_ips_mode;
@@ -611,6 +624,7 @@ fn warn_non_hot_changes(old: &ProxyConfig, new: &ProxyConfig, non_hot_changed: b
|| old.censorship.server_hello_delay_min_ms != new.censorship.server_hello_delay_min_ms
|| old.censorship.server_hello_delay_max_ms != new.censorship.server_hello_delay_max_ms
|| old.censorship.tls_new_session_tickets != new.censorship.tls_new_session_tickets
|| old.censorship.serverhello_compact != new.censorship.serverhello_compact
|| old.censorship.tls_full_cert_ttl_secs != new.censorship.tls_full_cert_ttl_secs
|| old.censorship.alpn_enforce != new.censorship.alpn_enforce
|| old.censorship.mask_proxy_protocol != new.censorship.mask_proxy_protocol
@@ -1046,6 +1060,8 @@ fn log_changes(
!= new_hot.me_route_backpressure_high_timeout_ms
|| old_hot.me_route_backpressure_high_watermark_pct
!= new_hot.me_route_backpressure_high_watermark_pct
|| old_hot.me_route_backpressure_enabled != new_hot.me_route_backpressure_enabled
|| old_hot.me_route_fairshare_enabled != new_hot.me_route_fairshare_enabled
|| old_hot.me_reader_route_data_wait_ms != new_hot.me_reader_route_data_wait_ms
|| old_hot.me_health_interval_ms_unhealthy != new_hot.me_health_interval_ms_unhealthy
|| old_hot.me_health_interval_ms_healthy != new_hot.me_health_interval_ms_healthy
@@ -1053,10 +1069,12 @@ fn log_changes(
|| old_hot.me_warn_rate_limit_ms != new_hot.me_warn_rate_limit_ms
{
info!(
"config reload: me_route_backpressure: base={}ms high={}ms watermark={}%; me_reader_route_data_wait_ms={}; me_health_interval: unhealthy={}ms healthy={}ms; me_admission_poll={}ms; me_warn_rate_limit={}ms",
"config reload: me_route_backpressure: enabled={} base={}ms high={}ms watermark={}%; me_route_fairshare_enabled={}; me_reader_route_data_wait_ms={}; me_health_interval: unhealthy={}ms healthy={}ms; me_admission_poll={}ms; me_warn_rate_limit={}ms",
new_hot.me_route_backpressure_enabled,
new_hot.me_route_backpressure_base_timeout_ms,
new_hot.me_route_backpressure_high_timeout_ms,
new_hot.me_route_backpressure_high_watermark_pct,
new_hot.me_route_fairshare_enabled,
new_hot.me_reader_route_data_wait_ms,
new_hot.me_health_interval_ms_unhealthy,
new_hot.me_health_interval_ms_healthy,
@@ -1183,6 +1201,18 @@ fn log_changes(
new_hot.user_data_quota.len()
);
}
if old_hot.user_rate_limits != new_hot.user_rate_limits {
info!(
"config reload: user_rate_limits updated ({} entries)",
new_hot.user_rate_limits.len()
);
}
if old_hot.cidr_rate_limits != new_hot.cidr_rate_limits {
info!(
"config reload: cidr_rate_limits updated ({} entries)",
new_hot.cidr_rate_limits.len()
);
}
if old_hot.user_max_unique_ips != new_hot.user_max_unique_ips {
info!(
"config reload: user_max_unique_ips updated ({} entries)",

View File

@@ -343,6 +343,10 @@ impl ProxyConfig {
let network_table = parsed_toml
.get("network")
.and_then(|value| value.as_table());
let server_table = parsed_toml.get("server").and_then(|value| value.as_table());
let conntrack_control_table = server_table
.and_then(|table| table.get("conntrack_control"))
.and_then(|value| value.as_table());
let update_every_is_explicit = general_table
.map(|table| table.contains_key("update_every"))
.unwrap_or(false);
@@ -372,10 +376,17 @@ impl ProxyConfig {
let stun_servers_is_explicit = network_table
.map(|table| table.contains_key("stun_servers"))
.unwrap_or(false);
let inline_conntrack_control_is_explicit = conntrack_control_table
.map(|table| table.contains_key("inline_conntrack_control"))
.unwrap_or(false);
let mut config: ProxyConfig = parsed_toml
.try_into()
.map_err(|e| ProxyError::Config(e.to_string()))?;
config
.server
.conntrack_control
.inline_conntrack_control_explicit = inline_conntrack_control_is_explicit;
if !update_every_is_explicit && (legacy_secret_is_explicit || legacy_config_is_explicit) {
config.general.update_every = None;
@@ -629,12 +640,6 @@ impl ProxyConfig {
));
}
if config.censorship.mask_relay_max_bytes == 0 {
return Err(ProxyError::Config(
"censorship.mask_relay_max_bytes must be > 0".to_string(),
));
}
if config.censorship.mask_relay_max_bytes > 67_108_864 {
return Err(ProxyError::Config(
"censorship.mask_relay_max_bytes must be <= 67108864".to_string(),
@@ -861,6 +866,22 @@ impl ProxyConfig {
));
}
for (user, limit) in &config.access.user_rate_limits {
if limit.up_bps == 0 && limit.down_bps == 0 {
return Err(ProxyError::Config(format!(
"access.user_rate_limits.{user} must set at least one non-zero direction"
)));
}
}
for (cidr, limit) in &config.access.cidr_rate_limits {
if limit.up_bps == 0 && limit.down_bps == 0 {
return Err(ProxyError::Config(format!(
"access.cidr_rate_limits.{cidr} must set at least one non-zero direction"
)));
}
}
if config.general.me_reinit_every_secs == 0 {
return Err(ProxyError::Config(
"general.me_reinit_every_secs must be > 0".to_string(),
@@ -1865,6 +1886,43 @@ mod tests {
);
}
#[test]
fn conntrack_inline_explicit_flag_is_false_when_omitted() {
let cfg = load_config_from_temp_toml(
r#"
[general]
[network]
[server]
[server.conntrack_control]
[access]
"#,
);
assert!(
!cfg.server
.conntrack_control
.inline_conntrack_control_explicit
);
}
#[test]
fn conntrack_inline_explicit_flag_is_true_when_present() {
let cfg = load_config_from_temp_toml(
r#"
[general]
[network]
[server]
[server.conntrack_control]
inline_conntrack_control = true
[access]
"#,
);
assert!(
cfg.server
.conntrack_control
.inline_conntrack_control_explicit
);
}
#[test]
fn unknown_sni_action_parses_and_defaults_to_drop() {
let cfg_default: ProxyConfig = toml::from_str(
@@ -1913,6 +1971,22 @@ mod tests {
cfg_accept.censorship.unknown_sni_action,
UnknownSniAction::Accept
);
let cfg_reject: ProxyConfig = toml::from_str(
r#"
[server]
[general]
[network]
[access]
[censorship]
unknown_sni_action = "reject_handshake"
"#,
)
.unwrap();
assert_eq!(
cfg_reject.censorship.unknown_sni_action,
UnknownSniAction::RejectHandshake
);
}
#[test]

View File

@@ -238,7 +238,7 @@ mask_shape_above_cap_blur_max_bytes = 8
}
#[test]
fn load_rejects_zero_mask_relay_max_bytes() {
fn load_accepts_zero_mask_relay_max_bytes_as_unlimited() {
let path = write_temp_config(
r#"
[censorship]
@@ -246,12 +246,9 @@ mask_relay_max_bytes = 0
"#,
);
let err = ProxyConfig::load(&path).expect_err("mask_relay_max_bytes must be > 0");
let msg = err.to_string();
assert!(
msg.contains("censorship.mask_relay_max_bytes must be > 0"),
"error must explain non-zero relay cap invariant, got: {msg}"
);
let cfg = ProxyConfig::load(&path)
.expect("mask_relay_max_bytes=0 must be accepted as unlimited relay cap");
assert_eq!(cfg.censorship.mask_relay_max_bytes, 0);
remove_temp_config(&path);
}

View File

@@ -392,14 +392,26 @@ pub struct GeneralConfig {
#[serde(default = "default_proxy_secret_path")]
pub proxy_secret_path: Option<String>,
/// Optional custom URL for infrastructure secret (https://core.telegram.org/getProxySecret if absent).
#[serde(default)]
pub proxy_secret_url: Option<String>,
/// Optional path to cache raw getProxyConfig (IPv4) snapshot for startup fallback.
#[serde(default = "default_proxy_config_v4_cache_path")]
pub proxy_config_v4_cache_path: Option<String>,
/// Optional custom URL for getProxyConfig (https://core.telegram.org/getProxyConfig if absent).
#[serde(default)]
pub proxy_config_v4_url: Option<String>,
/// Optional path to cache raw getProxyConfigV6 snapshot for startup fallback.
#[serde(default = "default_proxy_config_v6_cache_path")]
pub proxy_config_v6_cache_path: Option<String>,
/// Optional custom URL for getProxyConfigV6 (https://core.telegram.org/getProxyConfigV6 if absent).
#[serde(default)]
pub proxy_config_v6_url: Option<String>,
/// Global ad_tag (32 hex chars from @MTProxybot). Fallback when user has no per-user tag in access.user_ad_tags.
#[serde(default)]
pub ad_tag: Option<String>,
@@ -717,6 +729,14 @@ pub struct GeneralConfig {
#[serde(default)]
pub me_socks_kdf_policy: MeSocksKdfPolicy,
/// Enable route-level ME backpressure controls in reader fairness path.
#[serde(default = "default_me_route_backpressure_enabled")]
pub me_route_backpressure_enabled: bool,
/// Enable worker-local fairshare scheduler for ME reader routing.
#[serde(default = "default_me_route_fairshare_enabled")]
pub me_route_fairshare_enabled: bool,
/// Base backpressure timeout in milliseconds for ME route channel send.
#[serde(default = "default_me_route_backpressure_base_timeout_ms")]
pub me_route_backpressure_base_timeout_ms: u64,
@@ -960,8 +980,11 @@ impl Default for GeneralConfig {
use_middle_proxy: default_true(),
ad_tag: None,
proxy_secret_path: default_proxy_secret_path(),
proxy_secret_url: None,
proxy_config_v4_cache_path: default_proxy_config_v4_cache_path(),
proxy_config_v4_url: None,
proxy_config_v6_cache_path: default_proxy_config_v6_cache_path(),
proxy_config_v6_url: None,
middle_proxy_nat_ip: None,
middle_proxy_nat_probe: default_true(),
middle_proxy_nat_stun: default_middle_proxy_nat_stun(),
@@ -1044,6 +1067,8 @@ impl Default for GeneralConfig {
disable_colors: false,
telemetry: TelemetryConfig::default(),
me_socks_kdf_policy: MeSocksKdfPolicy::Strict,
me_route_backpressure_enabled: default_me_route_backpressure_enabled(),
me_route_fairshare_enabled: default_me_route_fairshare_enabled(),
me_route_backpressure_base_timeout_ms: default_me_route_backpressure_base_timeout_ms(),
me_route_backpressure_high_timeout_ms: default_me_route_backpressure_high_timeout_ms(),
me_route_backpressure_high_watermark_pct:
@@ -1329,6 +1354,10 @@ pub struct ConntrackControlConfig {
#[serde(default = "default_conntrack_control_enabled")]
pub inline_conntrack_control: bool,
/// Tracks whether inline_conntrack_control was explicitly set in config.
#[serde(skip)]
pub inline_conntrack_control_explicit: bool,
/// Conntrack mode for listener ingress traffic.
#[serde(default)]
pub mode: ConntrackMode,
@@ -1363,6 +1392,7 @@ impl Default for ConntrackControlConfig {
fn default() -> Self {
Self {
inline_conntrack_control: default_conntrack_control_enabled(),
inline_conntrack_control_explicit: false,
mode: ConntrackMode::default(),
backend: ConntrackBackend::default(),
profile: ConntrackPressureProfile::default(),
@@ -1551,6 +1581,13 @@ pub enum UnknownSniAction {
Drop,
Mask,
Accept,
/// Reject the TLS handshake by sending a fatal `unrecognized_name` alert
/// (RFC 6066, AlertDescription = 112) before closing the connection.
/// Mimics nginx `ssl_reject_handshake on;` behavior on the default vhost —
/// the wire response indistinguishable from a stock modern web server
/// that simply does not host the requested name.
#[serde(rename = "reject_handshake")]
RejectHandshake,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
@@ -1686,9 +1723,16 @@ pub struct AntiCensorshipConfig {
#[serde(default = "default_tls_new_session_tickets")]
pub tls_new_session_tickets: u8,
/// Enable compact ServerHello payload mode.
/// When false, FakeTLS always uses full ServerHello payload behavior.
/// When true, compact certificate payload mode can be used by TTL policy.
#[serde(default = "default_serverhello_compact")]
pub serverhello_compact: bool,
/// TTL in seconds for sending full certificate payload per client IP.
/// First client connection per (SNI domain, client IP) gets full cert payload.
/// Subsequent handshakes within TTL use compact cert metadata payload.
/// Applied only when `serverhello_compact` is enabled.
#[serde(default = "default_tls_full_cert_ttl_secs")]
pub tls_full_cert_ttl_secs: u64,
@@ -1731,6 +1775,7 @@ pub struct AntiCensorshipConfig {
pub mask_shape_above_cap_blur_max_bytes: usize,
/// Maximum bytes relayed per direction on unauthenticated masking fallback paths.
/// Set to 0 to disable byte cap (unlimited within relay/idle timeouts).
#[serde(default = "default_mask_relay_max_bytes")]
pub mask_relay_max_bytes: usize,
@@ -1782,6 +1827,7 @@ impl Default for AntiCensorshipConfig {
server_hello_delay_min_ms: default_server_hello_delay_min_ms(),
server_hello_delay_max_ms: default_server_hello_delay_max_ms(),
tls_new_session_tickets: default_tls_new_session_tickets(),
serverhello_compact: default_serverhello_compact(),
tls_full_cert_ttl_secs: default_tls_full_cert_ttl_secs(),
alpn_enforce: default_alpn_enforce(),
mask_proxy_protocol: 0,
@@ -1826,6 +1872,21 @@ pub struct AccessConfig {
#[serde(default)]
pub user_data_quota: HashMap<String, u64>,
/// Per-user transport rate limits in bits-per-second.
///
/// Each entry supports independent upload (`up_bps`) and download
/// (`down_bps`) ceilings. A value of `0` in one direction means
/// "unlimited" for that direction.
#[serde(default)]
pub user_rate_limits: HashMap<String, RateLimitBps>,
/// Per-CIDR aggregate transport rate limits in bits-per-second.
///
/// Matching uses longest-prefix-wins semantics. A value of `0` in one
/// direction means "unlimited" for that direction.
#[serde(default)]
pub cidr_rate_limits: HashMap<IpNetwork, RateLimitBps>,
#[serde(default)]
pub user_max_unique_ips: HashMap<String, usize>,
@@ -1859,6 +1920,8 @@ impl Default for AccessConfig {
user_max_tcp_conns_global_each: default_user_max_tcp_conns_global_each(),
user_expirations: HashMap::new(),
user_data_quota: HashMap::new(),
user_rate_limits: HashMap::new(),
cidr_rate_limits: HashMap::new(),
user_max_unique_ips: HashMap::new(),
user_max_unique_ips_global_each: default_user_max_unique_ips_global_each(),
user_max_unique_ips_mode: UserMaxUniqueIpsMode::default(),
@@ -1870,6 +1933,14 @@ impl Default for AccessConfig {
}
}
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct RateLimitBps {
#[serde(default)]
pub up_bps: u64,
#[serde(default)]
pub down_bps: u64,
}
// ============= Aux Structures =============
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]

View File

@@ -24,6 +24,13 @@ enum NetfilterBackend {
Iptables,
}
#[derive(Clone, Copy)]
struct ConntrackRuntimeSupport {
netfilter_backend: Option<NetfilterBackend>,
has_cap_net_admin: bool,
has_conntrack_binary: bool,
}
#[derive(Clone, Copy)]
struct PressureSample {
conn_pct: Option<u8>,
@@ -56,11 +63,8 @@ pub(crate) fn spawn_conntrack_controller(
shared: Arc<ProxySharedState>,
) {
if !cfg!(target_os = "linux") {
let enabled = config_rx
.borrow()
.server
.conntrack_control
.inline_conntrack_control;
let cfg = config_rx.borrow();
let enabled = cfg.server.conntrack_control.inline_conntrack_control;
stats.set_conntrack_control_enabled(enabled);
stats.set_conntrack_control_available(false);
stats.set_conntrack_pressure_active(false);
@@ -68,9 +72,14 @@ pub(crate) fn spawn_conntrack_controller(
stats.set_conntrack_rule_apply_ok(false);
shared.disable_conntrack_close_sender();
shared.set_conntrack_pressure_active(false);
if enabled {
if enabled
&& cfg
.server
.conntrack_control
.inline_conntrack_control_explicit
{
warn!(
"conntrack control is configured but unsupported on this OS; disabling runtime worker"
"conntrack control explicitly enabled but unsupported on this OS; disabling runtime worker"
);
}
return;
@@ -92,16 +101,17 @@ async fn run_conntrack_controller(
let mut cfg = config_rx.borrow().clone();
let mut pressure_state = PressureState::new(stats.as_ref());
let mut delete_budget_tokens = cfg.server.conntrack_control.delete_budget_per_sec;
let mut backend = pick_backend(cfg.server.conntrack_control.backend);
let mut runtime_support = probe_runtime_support(cfg.server.conntrack_control.backend);
let mut effective_enabled = effective_conntrack_enabled(&cfg, runtime_support);
apply_runtime_state(
stats.as_ref(),
shared.as_ref(),
&cfg,
backend.is_some(),
runtime_support,
false,
);
reconcile_rules(&cfg, backend, stats.as_ref()).await;
reconcile_rules(&cfg, runtime_support, stats.as_ref()).await;
loop {
tokio::select! {
@@ -110,17 +120,18 @@ async fn run_conntrack_controller(
break;
}
cfg = config_rx.borrow_and_update().clone();
backend = pick_backend(cfg.server.conntrack_control.backend);
runtime_support = probe_runtime_support(cfg.server.conntrack_control.backend);
effective_enabled = effective_conntrack_enabled(&cfg, runtime_support);
delete_budget_tokens = cfg.server.conntrack_control.delete_budget_per_sec;
apply_runtime_state(stats.as_ref(), shared.as_ref(), &cfg, backend.is_some(), pressure_state.active);
reconcile_rules(&cfg, backend, stats.as_ref()).await;
apply_runtime_state(stats.as_ref(), shared.as_ref(), &cfg, runtime_support, pressure_state.active);
reconcile_rules(&cfg, runtime_support, stats.as_ref()).await;
}
event = close_rx.recv() => {
let Some(event) = event else {
break;
};
stats.set_conntrack_event_queue_depth(close_rx.len() as u64);
if !cfg.server.conntrack_control.inline_conntrack_control {
if !effective_enabled {
continue;
}
if !pressure_state.active {
@@ -156,6 +167,7 @@ async fn run_conntrack_controller(
stats.as_ref(),
shared.as_ref(),
&cfg,
effective_enabled,
&sample,
&mut pressure_state,
);
@@ -175,20 +187,30 @@ fn apply_runtime_state(
stats: &Stats,
shared: &ProxySharedState,
cfg: &ProxyConfig,
backend_available: bool,
runtime_support: ConntrackRuntimeSupport,
pressure_active: bool,
) {
let enabled = cfg.server.conntrack_control.inline_conntrack_control;
let available = enabled && backend_available && has_cap_net_admin();
if enabled && !available {
let available = effective_conntrack_enabled(cfg, runtime_support);
if enabled
&& !available
&& cfg
.server
.conntrack_control
.inline_conntrack_control_explicit
{
warn!(
"conntrack control enabled but unavailable (missing CAP_NET_ADMIN or backend binaries)"
has_cap_net_admin = runtime_support.has_cap_net_admin,
backend_available = runtime_support.netfilter_backend.is_some(),
conntrack_binary_available = runtime_support.has_conntrack_binary,
configured_backend = ?cfg.server.conntrack_control.backend,
"conntrack control explicitly enabled but unavailable; disabling runtime features"
);
}
stats.set_conntrack_control_enabled(enabled);
stats.set_conntrack_control_available(available);
shared.set_conntrack_pressure_active(enabled && pressure_active);
stats.set_conntrack_pressure_active(enabled && pressure_active);
shared.set_conntrack_pressure_active(available && pressure_active);
stats.set_conntrack_pressure_active(available && pressure_active);
}
fn collect_pressure_sample(
@@ -228,10 +250,11 @@ fn update_pressure_state(
stats: &Stats,
shared: &ProxySharedState,
cfg: &ProxyConfig,
effective_enabled: bool,
sample: &PressureSample,
state: &mut PressureState,
) {
if !cfg.server.conntrack_control.inline_conntrack_control {
if !effective_enabled {
if state.active {
state.active = false;
state.low_streak = 0;
@@ -285,22 +308,26 @@ fn update_pressure_state(
state.low_streak = 0;
}
async fn reconcile_rules(cfg: &ProxyConfig, backend: Option<NetfilterBackend>, stats: &Stats) {
async fn reconcile_rules(
cfg: &ProxyConfig,
runtime_support: ConntrackRuntimeSupport,
stats: &Stats,
) {
if !cfg.server.conntrack_control.inline_conntrack_control {
clear_notrack_rules_all_backends().await;
stats.set_conntrack_rule_apply_ok(true);
return;
}
if !has_cap_net_admin() {
if !effective_conntrack_enabled(cfg, runtime_support) {
clear_notrack_rules_all_backends().await;
stats.set_conntrack_rule_apply_ok(false);
return;
}
let Some(backend) = backend else {
stats.set_conntrack_rule_apply_ok(false);
return;
};
let backend = runtime_support
.netfilter_backend
.expect("netfilter backend must be available for effective conntrack control");
let apply_result = match backend {
NetfilterBackend::Nftables => apply_nft_rules(cfg).await,
@@ -315,6 +342,24 @@ async fn reconcile_rules(cfg: &ProxyConfig, backend: Option<NetfilterBackend>, s
}
}
fn probe_runtime_support(configured_backend: ConntrackBackend) -> ConntrackRuntimeSupport {
ConntrackRuntimeSupport {
netfilter_backend: pick_backend(configured_backend),
has_cap_net_admin: has_cap_net_admin(),
has_conntrack_binary: command_exists("conntrack"),
}
}
fn effective_conntrack_enabled(
cfg: &ProxyConfig,
runtime_support: ConntrackRuntimeSupport,
) -> bool {
cfg.server.conntrack_control.inline_conntrack_control
&& runtime_support.has_cap_net_admin
&& runtime_support.netfilter_backend.is_some()
&& runtime_support.has_conntrack_binary
}
fn pick_backend(configured: ConntrackBackend) -> Option<NetfilterBackend> {
match configured {
ConntrackBackend::Auto => {
@@ -710,7 +755,7 @@ mod tests {
me_queue_pressure_delta: 0,
};
update_pressure_state(&stats, shared.as_ref(), &cfg, &sample, &mut state);
update_pressure_state(&stats, shared.as_ref(), &cfg, true, &sample, &mut state);
assert!(state.active);
assert!(shared.conntrack_pressure_active());
@@ -731,7 +776,14 @@ mod tests {
accept_timeout_delta: 0,
me_queue_pressure_delta: 0,
};
update_pressure_state(&stats, shared.as_ref(), &cfg, &high_sample, &mut state);
update_pressure_state(
&stats,
shared.as_ref(),
&cfg,
true,
&high_sample,
&mut state,
);
assert!(state.active);
let low_sample = PressureSample {
@@ -740,11 +792,11 @@ mod tests {
accept_timeout_delta: 0,
me_queue_pressure_delta: 0,
};
update_pressure_state(&stats, shared.as_ref(), &cfg, &low_sample, &mut state);
update_pressure_state(&stats, shared.as_ref(), &cfg, true, &low_sample, &mut state);
assert!(state.active);
update_pressure_state(&stats, shared.as_ref(), &cfg, &low_sample, &mut state);
update_pressure_state(&stats, shared.as_ref(), &cfg, true, &low_sample, &mut state);
assert!(state.active);
update_pressure_state(&stats, shared.as_ref(), &cfg, &low_sample, &mut state);
update_pressure_state(&stats, shared.as_ref(), &cfg, true, &low_sample, &mut state);
assert!(!state.active);
assert!(!shared.conntrack_pressure_active());
@@ -765,7 +817,7 @@ mod tests {
me_queue_pressure_delta: 10,
};
update_pressure_state(&stats, shared.as_ref(), &cfg, &sample, &mut state);
update_pressure_state(&stats, shared.as_ref(), &cfg, false, &sample, &mut state);
assert!(!state.active);
assert!(!shared.conntrack_pressure_active());

View File

@@ -8,6 +8,7 @@ use std::io::{self, Read, Write};
use std::os::unix::fs::OpenOptionsExt;
use std::path::{Path, PathBuf};
use nix::errno::Errno;
use nix::fcntl::{Flock, FlockArg};
use nix::unistd::{self, ForkResult, Gid, Pid, Uid, chdir, close, fork, getpid, setsid};
use tracing::{debug, info, warn};
@@ -157,15 +158,15 @@ fn redirect_stdio_to_devnull() -> Result<(), DaemonError> {
unsafe {
// Redirect stdin (fd 0)
if libc::dup2(devnull_fd, 0) < 0 {
return Err(DaemonError::RedirectFailed(nix::errno::Errno::last()));
return Err(DaemonError::RedirectFailed(Errno::last()));
}
// Redirect stdout (fd 1)
if libc::dup2(devnull_fd, 1) < 0 {
return Err(DaemonError::RedirectFailed(nix::errno::Errno::last()));
return Err(DaemonError::RedirectFailed(Errno::last()));
}
// Redirect stderr (fd 2)
if libc::dup2(devnull_fd, 2) < 0 {
return Err(DaemonError::RedirectFailed(nix::errno::Errno::last()));
return Err(DaemonError::RedirectFailed(Errno::last()));
}
}
@@ -337,6 +338,27 @@ fn is_process_running(pid: i32) -> bool {
nix::sys::signal::kill(Pid::from_raw(pid), None).is_ok()
}
// macOS gates nix::unistd::setgroups differently in the current dependency set,
// so call libc directly there while preserving the original nix path elsewhere.
fn set_supplementary_groups(gid: Gid) -> Result<(), nix::Error> {
#[cfg(target_os = "macos")]
{
let groups = [gid.as_raw()];
let rc = unsafe {
libc::setgroups(
i32::try_from(groups.len()).expect("single supplementary group must fit in c_int"),
groups.as_ptr(),
)
};
if rc == 0 { Ok(()) } else { Err(Errno::last()) }
}
#[cfg(not(target_os = "macos"))]
{
unistd::setgroups(&[gid])
}
}
/// Drops privileges to the specified user and group.
///
/// This should be called after binding privileged ports but before entering
@@ -368,7 +390,7 @@ pub fn drop_privileges(
if let Some(gid) = target_gid {
unistd::setgid(gid).map_err(DaemonError::PrivilegeDrop)?;
unistd::setgroups(&[gid]).map_err(DaemonError::PrivilegeDrop)?;
set_supplementary_groups(gid).map_err(DaemonError::PrivilegeDrop)?;
info!(gid = gid.as_raw(), "Dropped group privileges");
}

211
src/healthcheck.rs Normal file
View File

@@ -0,0 +1,211 @@
use std::io::{Read, Write};
use std::net::{Ipv4Addr, Ipv6Addr, SocketAddr, TcpStream};
use std::time::Duration;
use serde_json::Value;
use crate::config::ProxyConfig;
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(crate) enum HealthcheckMode {
Liveness,
Ready,
}
impl HealthcheckMode {
pub(crate) fn from_cli_arg(value: &str) -> Option<Self> {
match value {
"liveness" => Some(Self::Liveness),
"ready" => Some(Self::Ready),
_ => None,
}
}
fn request_path(self) -> &'static str {
match self {
Self::Liveness => "/v1/health",
Self::Ready => "/v1/health/ready",
}
}
}
pub(crate) fn run(config_path: &str, mode: HealthcheckMode) -> i32 {
match run_inner(config_path, mode) {
Ok(()) => 0,
Err(error) => {
eprintln!("[telemt] healthcheck failed: {error}");
1
}
}
}
fn run_inner(config_path: &str, mode: HealthcheckMode) -> Result<(), String> {
let config =
ProxyConfig::load(config_path).map_err(|error| format!("config load failed: {error}"))?;
let api_cfg = &config.server.api;
if !api_cfg.enabled {
return Ok(());
}
let listen: SocketAddr = api_cfg
.listen
.parse()
.map_err(|_| format!("invalid API listen address: {}", api_cfg.listen))?;
if listen.port() == 0 {
return Err("API listen port is 0".to_string());
}
let target = probe_target(listen);
let mut stream = TcpStream::connect_timeout(&target, Duration::from_secs(2))
.map_err(|error| format!("connect {target} failed: {error}"))?;
stream
.set_read_timeout(Some(Duration::from_secs(2)))
.map_err(|error| format!("set read timeout failed: {error}"))?;
stream
.set_write_timeout(Some(Duration::from_secs(2)))
.map_err(|error| format!("set write timeout failed: {error}"))?;
let request = build_request(target, mode.request_path(), &api_cfg.auth_header);
stream
.write_all(request.as_bytes())
.map_err(|error| format!("request write failed: {error}"))?;
stream
.flush()
.map_err(|error| format!("request flush failed: {error}"))?;
let mut raw_response = Vec::new();
stream
.read_to_end(&mut raw_response)
.map_err(|error| format!("response read failed: {error}"))?;
let response =
String::from_utf8(raw_response).map_err(|_| "response is not valid UTF-8".to_string())?;
let (status_code, body) = split_response(&response)?;
if status_code != 200 {
return Err(format!("HTTP status {status_code}"));
}
validate_payload(mode, body)?;
Ok(())
}
fn probe_target(listen: SocketAddr) -> SocketAddr {
match listen {
SocketAddr::V4(addr) => {
let ip = if addr.ip().is_unspecified() {
Ipv4Addr::LOCALHOST
} else {
*addr.ip()
};
SocketAddr::from((ip, addr.port()))
}
SocketAddr::V6(addr) => {
let ip = if addr.ip().is_unspecified() {
Ipv6Addr::LOCALHOST
} else {
*addr.ip()
};
SocketAddr::from((ip, addr.port()))
}
}
}
fn build_request(target: SocketAddr, path: &str, auth_header: &str) -> String {
let mut request = format!(
"GET {path} HTTP/1.1\r\nHost: {}\r\nConnection: close\r\n",
target
);
if !auth_header.is_empty() {
request.push_str("Authorization: ");
request.push_str(auth_header);
request.push_str("\r\n");
}
request.push_str("\r\n");
request
}
fn split_response(response: &str) -> Result<(u16, &str), String> {
let header_end = response
.find("\r\n\r\n")
.ok_or_else(|| "invalid HTTP response headers".to_string())?;
let header = &response[..header_end];
let body = &response[header_end + 4..];
let status_line = header
.lines()
.next()
.ok_or_else(|| "missing HTTP status line".to_string())?;
let status_code = parse_status_code(status_line)?;
Ok((status_code, body))
}
fn parse_status_code(status_line: &str) -> Result<u16, String> {
let mut parts = status_line.split_whitespace();
let version = parts
.next()
.ok_or_else(|| "missing HTTP version".to_string())?;
if !version.starts_with("HTTP/") {
return Err(format!("invalid HTTP status line: {status_line}"));
}
let code = parts
.next()
.ok_or_else(|| "missing HTTP status code".to_string())?;
code.parse::<u16>()
.map_err(|_| format!("invalid HTTP status code: {code}"))
}
fn validate_payload(mode: HealthcheckMode, body: &str) -> Result<(), String> {
let payload: Value =
serde_json::from_str(body).map_err(|_| "response body is not valid JSON".to_string())?;
if payload.get("ok").and_then(Value::as_bool) != Some(true) {
return Err("response JSON has ok=false".to_string());
}
let data = payload
.get("data")
.ok_or_else(|| "response JSON has no data field".to_string())?;
match mode {
HealthcheckMode::Liveness => {
if data.get("status").and_then(Value::as_str) != Some("ok") {
return Err("liveness status is not ok".to_string());
}
}
HealthcheckMode::Ready => {
if data.get("ready").and_then(Value::as_bool) != Some(true) {
return Err("readiness flag is false".to_string());
}
}
}
Ok(())
}
#[cfg(test)]
mod tests {
use super::{HealthcheckMode, parse_status_code, split_response, validate_payload};
#[test]
fn parse_status_code_reads_http_200() {
let status = parse_status_code("HTTP/1.1 200 OK").expect("must parse status");
assert_eq!(status, 200);
}
#[test]
fn split_response_extracts_status_and_body() {
let response = "HTTP/1.1 200 OK\r\nContent-Type: application/json\r\n\r\n{\"ok\":true}";
let (status, body) = split_response(response).expect("must split response");
assert_eq!(status, 200);
assert_eq!(body, "{\"ok\":true}");
}
#[test]
fn validate_payload_accepts_liveness_contract() {
let body = "{\"ok\":true,\"data\":{\"status\":\"ok\"}}";
validate_payload(HealthcheckMode::Liveness, body).expect("liveness payload must pass");
}
#[test]
fn validate_payload_rejects_not_ready() {
let body = "{\"ok\":true,\"data\":{\"ready\":false}}";
let result = validate_payload(HealthcheckMode::Ready, body);
assert!(result.is_err());
}
}

View File

@@ -231,7 +231,11 @@ fn print_help() {
#[cfg(test)]
mod tests {
use super::resolve_runtime_config_path;
use super::{
expected_handshake_close_description, is_expected_handshake_eof, peer_close_description,
resolve_runtime_config_path,
};
use crate::error::{ProxyError, StreamError};
#[test]
fn resolve_runtime_config_path_anchors_relative_to_startup_cwd() {
@@ -299,6 +303,81 @@ mod tests {
let _ = std::fs::remove_dir(&startup_cwd);
}
#[test]
fn expected_handshake_eof_matches_connection_reset() {
let err = ProxyError::Io(std::io::Error::from(std::io::ErrorKind::ConnectionReset));
assert!(is_expected_handshake_eof(&err));
}
#[test]
fn expected_handshake_eof_matches_stream_io_unexpected_eof() {
let err = ProxyError::Stream(StreamError::Io(std::io::Error::from(
std::io::ErrorKind::UnexpectedEof,
)));
assert!(is_expected_handshake_eof(&err));
}
#[test]
fn peer_close_description_is_human_readable_for_all_peer_close_kinds() {
let cases = [
(
std::io::ErrorKind::ConnectionReset,
"Peer reset TCP connection (RST)",
),
(
std::io::ErrorKind::ConnectionAborted,
"Peer aborted TCP connection during transport",
),
(
std::io::ErrorKind::BrokenPipe,
"Peer closed write side (broken pipe)",
),
(
std::io::ErrorKind::NotConnected,
"Socket was already closed by peer",
),
];
for (kind, expected) in cases {
let err = ProxyError::Io(std::io::Error::from(kind));
assert_eq!(peer_close_description(&err), Some(expected));
}
}
#[test]
fn handshake_close_description_is_human_readable_for_all_expected_kinds() {
let cases = [
(
ProxyError::Io(std::io::Error::from(std::io::ErrorKind::UnexpectedEof)),
"Peer closed before sending full 64-byte MTProto handshake",
),
(
ProxyError::Io(std::io::Error::from(std::io::ErrorKind::ConnectionReset)),
"Peer reset TCP connection during initial MTProto handshake",
),
(
ProxyError::Io(std::io::Error::from(std::io::ErrorKind::ConnectionAborted)),
"Peer aborted TCP connection during initial MTProto handshake",
),
(
ProxyError::Io(std::io::Error::from(std::io::ErrorKind::BrokenPipe)),
"Peer closed write side before MTProto handshake completed",
),
(
ProxyError::Io(std::io::Error::from(std::io::ErrorKind::NotConnected)),
"Handshake socket was already closed by peer",
),
(
ProxyError::Stream(StreamError::UnexpectedEof),
"Peer closed before sending full 64-byte MTProto handshake",
),
];
for (err, expected) in cases {
assert_eq!(expected_handshake_close_description(&err), Some(expected));
}
}
}
pub(crate) fn print_proxy_links(host: &str, port: u16, config: &ProxyConfig) {
@@ -428,7 +507,63 @@ pub(crate) async fn wait_until_admission_open(admission_rx: &mut watch::Receiver
}
pub(crate) fn is_expected_handshake_eof(err: &crate::error::ProxyError) -> bool {
err.to_string().contains("expected 64 bytes, got 0")
expected_handshake_close_description(err).is_some()
}
pub(crate) fn peer_close_description(err: &crate::error::ProxyError) -> Option<&'static str> {
fn from_kind(kind: std::io::ErrorKind) -> Option<&'static str> {
match kind {
std::io::ErrorKind::ConnectionReset => Some("Peer reset TCP connection (RST)"),
std::io::ErrorKind::ConnectionAborted => {
Some("Peer aborted TCP connection during transport")
}
std::io::ErrorKind::BrokenPipe => Some("Peer closed write side (broken pipe)"),
std::io::ErrorKind::NotConnected => Some("Socket was already closed by peer"),
_ => None,
}
}
match err {
crate::error::ProxyError::Io(ioe) => from_kind(ioe.kind()),
crate::error::ProxyError::Stream(crate::error::StreamError::Io(ioe)) => {
from_kind(ioe.kind())
}
_ => None,
}
}
pub(crate) fn expected_handshake_close_description(
err: &crate::error::ProxyError,
) -> Option<&'static str> {
fn from_kind(kind: std::io::ErrorKind) -> Option<&'static str> {
match kind {
std::io::ErrorKind::UnexpectedEof => {
Some("Peer closed before sending full 64-byte MTProto handshake")
}
std::io::ErrorKind::ConnectionReset => {
Some("Peer reset TCP connection during initial MTProto handshake")
}
std::io::ErrorKind::ConnectionAborted => {
Some("Peer aborted TCP connection during initial MTProto handshake")
}
std::io::ErrorKind::BrokenPipe => {
Some("Peer closed write side before MTProto handshake completed")
}
std::io::ErrorKind::NotConnected => Some("Handshake socket was already closed by peer"),
_ => None,
}
}
match err {
crate::error::ProxyError::Io(ioe) => from_kind(ioe.kind()),
crate::error::ProxyError::Stream(crate::error::StreamError::UnexpectedEof) => {
Some("Peer closed before sending full 64-byte MTProto handshake")
}
crate::error::ProxyError::Stream(crate::error::StreamError::Io(ioe)) => {
from_kind(ioe.kind())
}
_ => None,
}
}
pub(crate) async fn load_startup_proxy_config_snapshot(

View File

@@ -24,7 +24,10 @@ use crate::transport::middle_proxy::MePool;
use crate::transport::socket::set_linger_zero;
use crate::transport::{ListenOptions, UpstreamManager, create_listener, find_listener_processes};
use super::helpers::{is_expected_handshake_eof, print_proxy_links};
use super::helpers::{
expected_handshake_close_description, is_expected_handshake_eof, peer_close_description,
print_proxy_links,
};
pub(crate) struct BoundListeners {
pub(crate) listeners: Vec<(TcpListener, bool)>,
@@ -485,29 +488,9 @@ pub(crate) fn spawn_tcp_accept_loops(
Ok(guard) => *guard,
Err(_) => None,
};
let peer_closed = matches!(
&e,
crate::error::ProxyError::Io(ioe)
if matches!(
ioe.kind(),
std::io::ErrorKind::ConnectionReset
| std::io::ErrorKind::ConnectionAborted
| std::io::ErrorKind::BrokenPipe
| std::io::ErrorKind::NotConnected
)
) || matches!(
&e,
crate::error::ProxyError::Stream(
crate::error::StreamError::Io(ioe)
)
if matches!(
ioe.kind(),
std::io::ErrorKind::ConnectionReset
| std::io::ErrorKind::ConnectionAborted
| std::io::ErrorKind::BrokenPipe
| std::io::ErrorKind::NotConnected
)
);
let peer_close_reason = peer_close_description(&e);
let handshake_close_reason =
expected_handshake_close_description(&e);
let me_closed = matches!(
&e,
@@ -518,12 +501,23 @@ pub(crate) fn spawn_tcp_accept_loops(
crate::error::ProxyError::Proxy(msg) if msg == ROUTE_SWITCH_ERROR_MSG
);
match (peer_closed, me_closed) {
(true, _) => {
match (peer_close_reason, me_closed) {
(Some(reason), _) => {
if let Some(real_peer) = real_peer {
debug!(peer = %peer_addr, real_peer = %real_peer, error = %e, "Connection closed by client");
debug!(
peer = %peer_addr,
real_peer = %real_peer,
error = %e,
close_reason = reason,
"Connection closed by peer"
);
} else {
debug!(peer = %peer_addr, error = %e, "Connection closed by client");
debug!(
peer = %peer_addr,
error = %e,
close_reason = reason,
"Connection closed by peer"
);
}
}
(_, true) => {
@@ -541,10 +535,23 @@ pub(crate) fn spawn_tcp_accept_loops(
}
}
_ if is_expected_handshake_eof(&e) => {
let reason = handshake_close_reason
.unwrap_or("Peer closed during initial handshake");
if let Some(real_peer) = real_peer {
info!(peer = %peer_addr, real_peer = %real_peer, error = %e, "Connection closed during initial handshake");
info!(
peer = %peer_addr,
real_peer = %real_peer,
error = %e,
close_reason = reason,
"Connection closed during initial handshake"
);
} else {
info!(peer = %peer_addr, error = %e, "Connection closed during initial handshake");
info!(
peer = %peer_addr,
error = %e,
close_reason = reason,
"Connection closed during initial handshake"
);
}
}
_ => {

View File

@@ -66,6 +66,7 @@ pub(crate) async fn initialize_me_pool(
match crate::transport::middle_proxy::fetch_proxy_secret_with_upstream(
proxy_secret_path,
config.general.proxy_secret_len_max,
config.general.proxy_secret_url.as_deref(),
Some(upstream_manager.clone()),
)
.await
@@ -126,7 +127,11 @@ pub(crate) async fn initialize_me_pool(
.set_me_status(StartupMeStatus::Initializing, COMPONENT_ME_PROXY_CONFIG_V4)
.await;
let cfg_v4 = load_startup_proxy_config_snapshot(
"https://core.telegram.org/getProxyConfig",
config
.general
.proxy_config_v4_url
.as_deref()
.unwrap_or("https://core.telegram.org/getProxyConfig"),
config.general.proxy_config_v4_cache_path.as_deref(),
me2dc_fallback,
"getProxyConfig",
@@ -158,7 +163,11 @@ pub(crate) async fn initialize_me_pool(
.set_me_status(StartupMeStatus::Initializing, COMPONENT_ME_PROXY_CONFIG_V6)
.await;
let cfg_v6 = load_startup_proxy_config_snapshot(
"https://core.telegram.org/getProxyConfigV6",
config
.general
.proxy_config_v6_url
.as_deref()
.unwrap_or("https://core.telegram.org/getProxyConfigV6"),
config.general.proxy_config_v6_cache_path.as_deref(),
me2dc_fallback,
"getProxyConfigV6",
@@ -268,6 +277,8 @@ pub(crate) async fn initialize_me_pool(
config.general.me_socks_kdf_policy,
config.general.me_writer_cmd_channel_capacity,
config.general.me_route_channel_capacity,
config.general.me_route_backpressure_enabled,
config.general.me_route_fairshare_enabled,
config.general.me_route_backpressure_base_timeout_ms,
config.general.me_route_backpressure_high_timeout_ms,
config.general.me_route_backpressure_high_watermark_pct,

View File

@@ -664,6 +664,11 @@ async fn run_telemt_core(
));
let buffer_pool = Arc::new(BufferPool::with_config(64 * 1024, 4096));
let shared_state = ProxySharedState::new();
shared_state.traffic_limiter.apply_policy(
config.access.user_rate_limits.clone(),
config.access.cidr_rate_limits.clone(),
);
connectivity::run_startup_connectivity(
&config,
@@ -695,6 +700,7 @@ async fn run_telemt_core(
beobachten.clone(),
api_config_tx.clone(),
me_pool.clone(),
shared_state.clone(),
)
.await;
let config_rx = runtime_watches.config_rx;
@@ -711,7 +717,6 @@ async fn run_telemt_core(
)
.await;
let _admission_tx_hold = admission_tx;
let shared_state = ProxySharedState::new();
conntrack_control::spawn_conntrack_controller(
config_rx.clone(),
stats.clone(),

View File

@@ -51,6 +51,7 @@ pub(crate) async fn spawn_runtime_tasks(
beobachten: Arc<BeobachtenStore>,
api_config_tx: watch::Sender<Arc<ProxyConfig>>,
me_pool_for_policy: Option<Arc<MePool>>,
shared_state: Arc<ProxySharedState>,
) -> RuntimeWatches {
let um_clone = upstream_manager.clone();
let dc_overrides_for_health = config.dc_overrides.clone();
@@ -121,6 +122,8 @@ pub(crate) async fn spawn_runtime_tasks(
if let Some(pool) = &me_pool_for_policy {
pool.update_runtime_transport_policy(
cfg.general.me_socks_kdf_policy,
cfg.general.me_route_backpressure_enabled,
cfg.general.me_route_fairshare_enabled,
cfg.general.me_route_backpressure_base_timeout_ms,
cfg.general.me_route_backpressure_high_timeout_ms,
cfg.general.me_route_backpressure_high_watermark_pct,
@@ -182,6 +185,41 @@ pub(crate) async fn spawn_runtime_tasks(
}
});
let limiter = shared_state.traffic_limiter.clone();
limiter.apply_policy(
config.access.user_rate_limits.clone(),
config.access.cidr_rate_limits.clone(),
);
let mut config_rx_rate_limits = config_rx.clone();
tokio::spawn(async move {
let mut prev_user_limits = config_rx_rate_limits
.borrow()
.access
.user_rate_limits
.clone();
let mut prev_cidr_limits = config_rx_rate_limits
.borrow()
.access
.cidr_rate_limits
.clone();
loop {
if config_rx_rate_limits.changed().await.is_err() {
break;
}
let cfg = config_rx_rate_limits.borrow_and_update().clone();
if prev_user_limits != cfg.access.user_rate_limits
|| prev_cidr_limits != cfg.access.cidr_rate_limits
{
limiter.apply_policy(
cfg.access.user_rate_limits.clone(),
cfg.access.cidr_rate_limits.clone(),
);
prev_user_limits = cfg.access.user_rate_limits.clone();
prev_cidr_limits = cfg.access.cidr_rate_limits.clone();
}
}
});
let beobachten_writer = beobachten.clone();
let config_rx_beobachten = config_rx.clone();
tokio::spawn(async move {

View File

@@ -8,6 +8,7 @@ mod crypto;
#[cfg(unix)]
mod daemon;
mod error;
mod healthcheck;
mod ip_tracker;
#[cfg(test)]
#[path = "tests/ip_tracker_encapsulation_adversarial_tests.rs"]

View File

@@ -575,6 +575,139 @@ async fn render_metrics(
}
);
let limiter_metrics = shared_state.traffic_limiter.metrics_snapshot();
let _ = writeln!(
out,
"# HELP telemt_rate_limiter_throttle_total Traffic limiter throttle events by scope and direction"
);
let _ = writeln!(out, "# TYPE telemt_rate_limiter_throttle_total counter");
let _ = writeln!(
out,
"telemt_rate_limiter_throttle_total{{scope=\"user\",direction=\"up\"}} {}",
if core_enabled {
limiter_metrics.user_throttle_up_total
} else {
0
}
);
let _ = writeln!(
out,
"telemt_rate_limiter_throttle_total{{scope=\"user\",direction=\"down\"}} {}",
if core_enabled {
limiter_metrics.user_throttle_down_total
} else {
0
}
);
let _ = writeln!(
out,
"telemt_rate_limiter_throttle_total{{scope=\"cidr\",direction=\"up\"}} {}",
if core_enabled {
limiter_metrics.cidr_throttle_up_total
} else {
0
}
);
let _ = writeln!(
out,
"telemt_rate_limiter_throttle_total{{scope=\"cidr\",direction=\"down\"}} {}",
if core_enabled {
limiter_metrics.cidr_throttle_down_total
} else {
0
}
);
let _ = writeln!(
out,
"# HELP telemt_rate_limiter_wait_ms_total Traffic limiter accumulated wait time in milliseconds by scope and direction"
);
let _ = writeln!(out, "# TYPE telemt_rate_limiter_wait_ms_total counter");
let _ = writeln!(
out,
"telemt_rate_limiter_wait_ms_total{{scope=\"user\",direction=\"up\"}} {}",
if core_enabled {
limiter_metrics.user_wait_up_ms_total
} else {
0
}
);
let _ = writeln!(
out,
"telemt_rate_limiter_wait_ms_total{{scope=\"user\",direction=\"down\"}} {}",
if core_enabled {
limiter_metrics.user_wait_down_ms_total
} else {
0
}
);
let _ = writeln!(
out,
"telemt_rate_limiter_wait_ms_total{{scope=\"cidr\",direction=\"up\"}} {}",
if core_enabled {
limiter_metrics.cidr_wait_up_ms_total
} else {
0
}
);
let _ = writeln!(
out,
"telemt_rate_limiter_wait_ms_total{{scope=\"cidr\",direction=\"down\"}} {}",
if core_enabled {
limiter_metrics.cidr_wait_down_ms_total
} else {
0
}
);
let _ = writeln!(
out,
"# HELP telemt_rate_limiter_active_leases Active relay leases under rate limiting by scope"
);
let _ = writeln!(out, "# TYPE telemt_rate_limiter_active_leases gauge");
let _ = writeln!(
out,
"telemt_rate_limiter_active_leases{{scope=\"user\"}} {}",
if core_enabled {
limiter_metrics.user_active_leases
} else {
0
}
);
let _ = writeln!(
out,
"telemt_rate_limiter_active_leases{{scope=\"cidr\"}} {}",
if core_enabled {
limiter_metrics.cidr_active_leases
} else {
0
}
);
let _ = writeln!(
out,
"# HELP telemt_rate_limiter_policy_entries Active rate-limit policy entries by scope"
);
let _ = writeln!(out, "# TYPE telemt_rate_limiter_policy_entries gauge");
let _ = writeln!(
out,
"telemt_rate_limiter_policy_entries{{scope=\"user\"}} {}",
if core_enabled {
limiter_metrics.user_policy_entries
} else {
0
}
);
let _ = writeln!(
out,
"telemt_rate_limiter_policy_entries{{scope=\"cidr\"}} {}",
if core_enabled {
limiter_metrics.cidr_policy_entries
} else {
0
}
);
let _ = writeln!(
out,
"# HELP telemt_upstream_connect_attempt_total Upstream connect attempts across all requests"
@@ -1177,6 +1310,143 @@ async fn render_metrics(
0
}
);
let _ = writeln!(
out,
"# HELP telemt_me_fair_pressure_state Worker-local fairness pressure state"
);
let _ = writeln!(out, "# TYPE telemt_me_fair_pressure_state gauge");
let _ = writeln!(
out,
"telemt_me_fair_pressure_state {}",
if me_allows_normal {
stats.get_me_fair_pressure_state_gauge()
} else {
0
}
);
let _ = writeln!(
out,
"# HELP telemt_me_fair_active_flows Fair-scheduler active flow count"
);
let _ = writeln!(out, "# TYPE telemt_me_fair_active_flows gauge");
let _ = writeln!(
out,
"telemt_me_fair_active_flows {}",
if me_allows_normal {
stats.get_me_fair_active_flows_gauge()
} else {
0
}
);
let _ = writeln!(
out,
"# HELP telemt_me_fair_queued_bytes Fair-scheduler queued bytes"
);
let _ = writeln!(out, "# TYPE telemt_me_fair_queued_bytes gauge");
let _ = writeln!(
out,
"telemt_me_fair_queued_bytes {}",
if me_allows_normal {
stats.get_me_fair_queued_bytes_gauge()
} else {
0
}
);
let _ = writeln!(
out,
"# HELP telemt_me_fair_flow_state_gauge Fair-scheduler flow health classes"
);
let _ = writeln!(out, "# TYPE telemt_me_fair_flow_state_gauge gauge");
let _ = writeln!(
out,
"telemt_me_fair_flow_state_gauge{{class=\"standing\"}} {}",
if me_allows_normal {
stats.get_me_fair_standing_flows_gauge()
} else {
0
}
);
let _ = writeln!(
out,
"telemt_me_fair_flow_state_gauge{{class=\"backpressured\"}} {}",
if me_allows_normal {
stats.get_me_fair_backpressured_flows_gauge()
} else {
0
}
);
let _ = writeln!(
out,
"# HELP telemt_me_fair_events_total Fair-scheduler event counters"
);
let _ = writeln!(out, "# TYPE telemt_me_fair_events_total counter");
let _ = writeln!(
out,
"telemt_me_fair_events_total{{event=\"scheduler_round\"}} {}",
if me_allows_normal {
stats.get_me_fair_scheduler_rounds_total()
} else {
0
}
);
let _ = writeln!(
out,
"telemt_me_fair_events_total{{event=\"deficit_grant\"}} {}",
if me_allows_normal {
stats.get_me_fair_deficit_grants_total()
} else {
0
}
);
let _ = writeln!(
out,
"telemt_me_fair_events_total{{event=\"deficit_skip\"}} {}",
if me_allows_normal {
stats.get_me_fair_deficit_skips_total()
} else {
0
}
);
let _ = writeln!(
out,
"telemt_me_fair_events_total{{event=\"enqueue_reject\"}} {}",
if me_allows_normal {
stats.get_me_fair_enqueue_rejects_total()
} else {
0
}
);
let _ = writeln!(
out,
"telemt_me_fair_events_total{{event=\"shed_drop\"}} {}",
if me_allows_normal {
stats.get_me_fair_shed_drops_total()
} else {
0
}
);
let _ = writeln!(
out,
"telemt_me_fair_events_total{{event=\"penalty\"}} {}",
if me_allows_normal {
stats.get_me_fair_penalties_total()
} else {
0
}
);
let _ = writeln!(
out,
"telemt_me_fair_events_total{{event=\"downstream_stall\"}} {}",
if me_allows_normal {
stats.get_me_fair_downstream_stalls_total()
} else {
0
}
);
let _ = writeln!(
out,

View File

@@ -1383,6 +1383,8 @@ fn emulated_server_hello_never_places_alpn_in_server_hello_extensions() {
&session_id,
&cached,
false,
true,
ClientHelloTlsVersion::Tls13,
&rng,
Some(b"h2".to_vec()),
0,
@@ -1624,6 +1626,34 @@ fn test_extract_alpn_multiple() {
assert_eq!(alpn_str, vec!["h2", "spdy", "h3"]);
}
#[test]
fn detect_client_hello_tls_version_prefers_supported_versions_tls13() {
let supported_versions = vec![4, 0x03, 0x04, 0x03, 0x03];
let ch = build_client_hello_with_exts(vec![(0x002b, supported_versions)], "example.com");
assert_eq!(
detect_client_hello_tls_version(&ch),
Some(ClientHelloTlsVersion::Tls13)
);
}
#[test]
fn detect_client_hello_tls_version_falls_back_to_legacy_tls12() {
let ch = build_client_hello_with_exts(Vec::new(), "example.com");
assert_eq!(
detect_client_hello_tls_version(&ch),
Some(ClientHelloTlsVersion::Tls12)
);
}
#[test]
fn detect_client_hello_tls_version_rejects_malformed_supported_versions() {
// list_len=3 is invalid because version vector must contain u16 pairs.
let malformed_supported_versions = vec![3, 0x03, 0x04, 0x03];
let ch =
build_client_hello_with_exts(vec![(0x002b, malformed_supported_versions)], "example.com");
assert!(detect_client_hello_tls_version(&ch).is_none());
}
#[test]
fn extract_sni_rejects_zero_length_host_name() {
let mut sni_ext = Vec::new();

View File

@@ -811,6 +811,122 @@ pub fn extract_alpn_from_client_hello(handshake: &[u8]) -> Vec<Vec<u8>> {
out
}
/// ClientHello TLS generation inferred from handshake fields.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum ClientHelloTlsVersion {
Tls12,
Tls13,
}
/// Detect TLS generation from a ClientHello.
///
/// The parser prefers `supported_versions` (0x002b) when present and falls back
/// to `legacy_version` for compatibility with TLS 1.2 style hellos.
pub fn detect_client_hello_tls_version(handshake: &[u8]) -> Option<ClientHelloTlsVersion> {
if handshake.len() < 5 || handshake[0] != TLS_RECORD_HANDSHAKE {
return None;
}
let record_len = u16::from_be_bytes([handshake[3], handshake[4]]) as usize;
if handshake.len() < 5 + record_len {
return None;
}
let mut pos = 5; // after record header
if handshake.get(pos) != Some(&0x01) {
return None; // not ClientHello
}
pos += 1; // message type
if pos + 3 > handshake.len() {
return None;
}
let handshake_len = ((handshake[pos] as usize) << 16)
| ((handshake[pos + 1] as usize) << 8)
| handshake[pos + 2] as usize;
pos += 3; // handshake length bytes
if pos + handshake_len > 5 + record_len {
return None;
}
if pos + 2 + 32 > handshake.len() {
return None;
}
let legacy_version = u16::from_be_bytes([handshake[pos], handshake[pos + 1]]);
pos += 2 + 32; // version + random
let session_id_len = *handshake.get(pos)? as usize;
pos += 1 + session_id_len;
if pos + 2 > handshake.len() {
return None;
}
let cipher_len = u16::from_be_bytes([handshake[pos], handshake[pos + 1]]) as usize;
pos += 2 + cipher_len;
if pos >= handshake.len() {
return None;
}
let comp_len = *handshake.get(pos)? as usize;
pos += 1 + comp_len;
if pos + 2 > handshake.len() {
return None;
}
let ext_len = u16::from_be_bytes([handshake[pos], handshake[pos + 1]]) as usize;
pos += 2;
let ext_end = pos + ext_len;
if ext_end > handshake.len() {
return None;
}
while pos + 4 <= ext_end {
let etype = u16::from_be_bytes([handshake[pos], handshake[pos + 1]]);
let elen = u16::from_be_bytes([handshake[pos + 2], handshake[pos + 3]]) as usize;
pos += 4;
if pos + elen > ext_end {
return None;
}
if etype == extension_type::SUPPORTED_VERSIONS {
if elen < 1 {
return None;
}
let list_len = handshake[pos] as usize;
if list_len == 0 || list_len % 2 != 0 || 1 + list_len > elen {
return None;
}
let mut has_tls12 = false;
let mut ver_pos = pos + 1;
let ver_end = ver_pos + list_len;
while ver_pos + 1 < ver_end {
let version = u16::from_be_bytes([handshake[ver_pos], handshake[ver_pos + 1]]);
if version == 0x0304 {
return Some(ClientHelloTlsVersion::Tls13);
}
if version == 0x0303 || version == 0x0302 || version == 0x0301 {
has_tls12 = true;
}
ver_pos += 2;
}
if has_tls12 {
return Some(ClientHelloTlsVersion::Tls12);
}
return None;
}
pos += elen;
}
if legacy_version >= 0x0303 {
Some(ClientHelloTlsVersion::Tls12)
} else {
None
}
}
/// Check if bytes look like a TLS ClientHello
pub fn is_tls_handshake(first_bytes: &[u8]) -> bool {
if first_bytes.len() < 3 {

View File

@@ -324,17 +324,38 @@ fn record_beobachten_class(
beobachten.record(class, peer_ip, beobachten_ttl(config));
}
fn classify_expected_64_got_0(kind: std::io::ErrorKind) -> Option<&'static str> {
match kind {
std::io::ErrorKind::UnexpectedEof => Some("expected_64_got_0_unexpected_eof"),
std::io::ErrorKind::ConnectionReset => Some("expected_64_got_0_connection_reset"),
std::io::ErrorKind::ConnectionAborted => Some("expected_64_got_0_connection_aborted"),
std::io::ErrorKind::BrokenPipe => Some("expected_64_got_0_broken_pipe"),
std::io::ErrorKind::NotConnected => Some("expected_64_got_0_not_connected"),
_ => None,
}
}
fn classify_handshake_failure_class(error: &ProxyError) -> &'static str {
match error {
ProxyError::Io(err) => classify_expected_64_got_0(err.kind()).unwrap_or("other"),
ProxyError::Stream(StreamError::UnexpectedEof) => "expected_64_got_0_unexpected_eof",
ProxyError::Stream(StreamError::Io(err)) => {
classify_expected_64_got_0(err.kind()).unwrap_or("other")
}
_ => "other",
}
}
fn record_handshake_failure_class(
beobachten: &BeobachtenStore,
config: &ProxyConfig,
peer_ip: IpAddr,
error: &ProxyError,
) {
let class = match error {
ProxyError::Io(err) if err.kind() == std::io::ErrorKind::UnexpectedEof => {
"expected_64_got_0"
}
ProxyError::Stream(StreamError::UnexpectedEof) => "expected_64_got_0",
// Keep beobachten buckets stable while detailed per-kind classification
// is tracked in API counters.
let class = match classify_handshake_failure_class(error) {
value if value.starts_with("expected_64_got_0_") => "expected_64_got_0",
_ => "other",
};
record_beobachten_class(beobachten, config, peer_ip, class);
@@ -343,7 +364,7 @@ fn record_handshake_failure_class(
#[inline]
fn increment_bad_on_unknown_tls_sni(stats: &Stats, error: &ProxyError) {
if matches!(error, ProxyError::UnknownTlsSni) {
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("unknown_tls_sni");
}
}
@@ -444,7 +465,7 @@ where
Ok(Ok(info)) => {
if !is_trusted_proxy_source(peer.ip(), &config.server.proxy_protocol_trusted_cidrs)
{
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("proxy_protocol_untrusted");
warn!(
peer = %peer,
trusted = ?config.server.proxy_protocol_trusted_cidrs,
@@ -465,13 +486,13 @@ where
}
}
Ok(Err(e)) => {
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("proxy_protocol_invalid_header");
warn!(peer = %peer, error = %e, "Invalid PROXY protocol header");
record_beobachten_class(&beobachten, &config, peer.ip(), "other");
return Err(e);
}
Err(_) => {
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("proxy_protocol_header_timeout");
warn!(peer = %peer, timeout_ms = proxy_header_timeout.as_millis(), "PROXY protocol header timeout");
record_beobachten_class(&beobachten, &config, peer.ip(), "other");
return Err(ProxyError::InvalidProxyProtocol);
@@ -561,7 +582,7 @@ where
// third-party clients or future Telegram versions.
if !tls_clienthello_len_in_bounds(tls_len) {
debug!(peer = %real_peer, tls_len = tls_len, max_tls_len = MAX_TLS_PLAINTEXT_SIZE, "TLS handshake length out of bounds");
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("tls_clienthello_len_out_of_bounds");
maybe_apply_mask_reject_delay(&config).await;
let (reader, writer) = tokio::io::split(stream);
return Ok(masking_outcome(
@@ -581,7 +602,7 @@ where
Ok(n) => n,
Err(e) => {
debug!(peer = %real_peer, error = %e, tls_len = tls_len, "TLS ClientHello body read failed; engaging masking fallback");
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("tls_clienthello_read_error");
maybe_apply_mask_reject_delay(&config).await;
let initial_len = 5;
let (reader, writer) = tokio::io::split(stream);
@@ -599,7 +620,7 @@ where
if body_read < tls_len {
debug!(peer = %real_peer, got = body_read, expected = tls_len, "Truncated in-range TLS ClientHello; engaging masking fallback");
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("tls_clienthello_truncated");
maybe_apply_mask_reject_delay(&config).await;
let initial_len = 5 + body_read;
let (reader, writer) = tokio::io::split(stream);
@@ -623,7 +644,7 @@ where
).await {
HandshakeResult::Success(result) => result,
HandshakeResult::BadClient { reader, writer } => {
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("tls_handshake_bad_client");
return Ok(masking_outcome(
reader,
writer,
@@ -663,7 +684,7 @@ where
wrap_tls_application_record(&pending_plaintext)
};
let reader = tokio::io::AsyncReadExt::chain(std::io::Cursor::new(pending_record), reader);
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("tls_mtproto_bad_client");
debug!(
peer = %peer,
"Authenticated TLS session failed MTProto validation; engaging masking fallback"
@@ -693,7 +714,7 @@ where
} else {
if !config.general.modes.classic && !config.general.modes.secure {
debug!(peer = %real_peer, "Non-TLS modes disabled");
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("direct_modes_disabled");
maybe_apply_mask_reject_delay(&config).await;
let (reader, writer) = tokio::io::split(stream);
return Ok(masking_outcome(
@@ -720,7 +741,7 @@ where
).await {
HandshakeResult::Success(result) => result,
HandshakeResult::BadClient { reader, writer } => {
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("direct_mtproto_bad_client");
return Ok(masking_outcome(
reader,
writer,
@@ -757,6 +778,7 @@ where
Ok(Ok(outcome)) => outcome,
Ok(Err(e)) => {
debug!(peer = %peer, error = %e, "Handshake failed");
stats_for_timeout.increment_handshake_failure_class(classify_handshake_failure_class(&e));
record_handshake_failure_class(
&beobachten_for_timeout,
&config_for_timeout,
@@ -767,6 +789,7 @@ where
}
Err(_) => {
stats_for_timeout.increment_handshake_timeouts();
stats_for_timeout.increment_handshake_failure_class("timeout");
debug!(peer = %peer, "Handshake timeout");
record_beobachten_class(
&beobachten_for_timeout,
@@ -956,7 +979,8 @@ impl RunningClientHandler {
self.peer.ip(),
&self.config.server.proxy_protocol_trusted_cidrs,
) {
self.stats.increment_connects_bad();
self.stats
.increment_connects_bad_with_class("proxy_protocol_untrusted");
warn!(
peer = %self.peer,
trusted = ?self.config.server.proxy_protocol_trusted_cidrs,
@@ -986,7 +1010,8 @@ impl RunningClientHandler {
}
}
Ok(Err(e)) => {
self.stats.increment_connects_bad();
self.stats
.increment_connects_bad_with_class("proxy_protocol_invalid_header");
warn!(peer = %self.peer, error = %e, "Invalid PROXY protocol header");
record_beobachten_class(
&self.beobachten,
@@ -997,7 +1022,8 @@ impl RunningClientHandler {
return Err(e);
}
Err(_) => {
self.stats.increment_connects_bad();
self.stats
.increment_connects_bad_with_class("proxy_protocol_header_timeout");
warn!(
peer = %self.peer,
timeout_ms = proxy_header_timeout.as_millis(),
@@ -1095,6 +1121,7 @@ impl RunningClientHandler {
Ok(Ok(outcome)) => outcome,
Ok(Err(e)) => {
debug!(peer = %peer_for_log, error = %e, "Handshake failed");
stats.increment_handshake_failure_class(classify_handshake_failure_class(&e));
record_handshake_failure_class(
&beobachten_for_timeout,
&config_for_timeout,
@@ -1105,6 +1132,7 @@ impl RunningClientHandler {
}
Err(_) => {
stats.increment_handshake_timeouts();
stats.increment_handshake_failure_class("timeout");
debug!(peer = %peer_for_log, "Handshake timeout");
record_beobachten_class(
&beobachten_for_timeout,
@@ -1140,7 +1168,8 @@ impl RunningClientHandler {
// third-party clients or future Telegram versions.
if !tls_clienthello_len_in_bounds(tls_len) {
debug!(peer = %peer, tls_len = tls_len, max_tls_len = MAX_TLS_PLAINTEXT_SIZE, "TLS handshake length out of bounds");
self.stats.increment_connects_bad();
self.stats
.increment_connects_bad_with_class("tls_clienthello_len_out_of_bounds");
maybe_apply_mask_reject_delay(&self.config).await;
let (reader, writer) = self.stream.into_split();
return Ok(masking_outcome(
@@ -1160,7 +1189,8 @@ impl RunningClientHandler {
Ok(n) => n,
Err(e) => {
debug!(peer = %peer, error = %e, tls_len = tls_len, "TLS ClientHello body read failed; engaging masking fallback");
self.stats.increment_connects_bad();
self.stats
.increment_connects_bad_with_class("tls_clienthello_read_error");
maybe_apply_mask_reject_delay(&self.config).await;
let (reader, writer) = self.stream.into_split();
return Ok(masking_outcome(
@@ -1177,7 +1207,8 @@ impl RunningClientHandler {
if body_read < tls_len {
debug!(peer = %peer, got = body_read, expected = tls_len, "Truncated in-range TLS ClientHello; engaging masking fallback");
self.stats.increment_connects_bad();
self.stats
.increment_connects_bad_with_class("tls_clienthello_truncated");
maybe_apply_mask_reject_delay(&self.config).await;
let initial_len = 5 + body_read;
let (reader, writer) = self.stream.into_split();
@@ -1214,7 +1245,7 @@ impl RunningClientHandler {
{
HandshakeResult::Success(result) => result,
HandshakeResult::BadClient { reader, writer } => {
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("tls_handshake_bad_client");
return Ok(masking_outcome(
reader,
writer,
@@ -1264,7 +1295,7 @@ impl RunningClientHandler {
};
let reader =
tokio::io::AsyncReadExt::chain(std::io::Cursor::new(pending_record), reader);
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("tls_mtproto_bad_client");
debug!(
peer = %peer,
"Authenticated TLS session failed MTProto validation; engaging masking fallback"
@@ -1311,7 +1342,8 @@ impl RunningClientHandler {
if !self.config.general.modes.classic && !self.config.general.modes.secure {
debug!(peer = %peer, "Non-TLS modes disabled");
self.stats.increment_connects_bad();
self.stats
.increment_connects_bad_with_class("direct_modes_disabled");
maybe_apply_mask_reject_delay(&self.config).await;
let (reader, writer) = self.stream.into_split();
return Ok(masking_outcome(
@@ -1351,7 +1383,7 @@ impl RunningClientHandler {
{
HandshakeResult::Success(result) => result,
HandshakeResult::BadClient { reader, writer } => {
stats.increment_connects_bad();
stats.increment_connects_bad_with_class("direct_mtproto_bad_client");
return Ok(masking_outcome(
reader,
writer,

View File

@@ -316,6 +316,9 @@ where
stats.increment_user_connects(user);
let _direct_connection_lease = stats.acquire_direct_connection_lease();
let traffic_lease = shared
.traffic_limiter
.acquire_lease(user, success.peer.ip());
let buffer_pool_trim = Arc::clone(&buffer_pool);
let relay_activity_timeout = if shared.conntrack_pressure_active() {
@@ -329,7 +332,7 @@ where
} else {
Duration::from_secs(1800)
};
let relay_result = crate::proxy::relay::relay_bidirectional_with_activity_timeout(
let relay_result = crate::proxy::relay::relay_bidirectional_with_activity_timeout_and_lease(
client_reader,
client_writer,
tg_reader,
@@ -340,6 +343,7 @@ where
Arc::clone(&stats),
config.access.user_data_quota.get(user).copied(),
buffer_pool,
traffic_lease,
relay_activity_timeout,
);
tokio::pin!(relay_result);

View File

@@ -1119,6 +1119,10 @@ where
} else {
None
};
// Fail-closed to TLS 1.3 semantics when ClientHello version is ambiguous:
// this avoids leaking certificate payload on malformed probes.
let client_tls_version = tls::detect_client_hello_tls_version(handshake)
.unwrap_or(tls::ClientHelloTlsVersion::Tls13);
if client_sni.is_some() && matched_tls_domain.is_none() && preferred_user_hint.is_none() {
let sni = client_sni.as_deref().unwrap_or_default();
@@ -1132,9 +1136,20 @@ where
"TLS handshake accepted by unknown SNI policy"
);
}
action @ (UnknownSniAction::Drop | UnknownSniAction::Mask) => {
action @ (UnknownSniAction::Drop
| UnknownSniAction::Mask
| UnknownSniAction::RejectHandshake) => {
auth_probe_record_failure_in(shared, peer.ip(), Instant::now());
maybe_apply_server_hello_delay(config).await;
// For Drop/Mask we apply the synthetic ServerHello delay so
// the fail-closed path is timing-indistinguishable from the
// success path. For RejectHandshake we deliberately skip the
// delay: a stock modern nginx with `ssl_reject_handshake on;`
// responds with the alert essentially immediately, so
// injecting 8-24ms here would itself become a distinguisher
// against the public baseline we are trying to blend into.
if !matches!(action, UnknownSniAction::RejectHandshake) {
maybe_apply_server_hello_delay(config).await;
}
let log_now = Instant::now();
if should_emit_unknown_sni_warn_in(shared, log_now) {
warn!(
@@ -1153,8 +1168,33 @@ where
"TLS handshake rejected by unknown SNI policy"
);
}
if matches!(action, UnknownSniAction::RejectHandshake) {
// TLS alert record layer:
// 0x15 ContentType.alert
// 0x03 0x03 legacy_record_version = TLS 1.2
// (matches what modern nginx emits in
// the first server -> client record,
// per RFC 8446 5.1 guidance)
// 0x00 0x02 length = 2
// Alert payload:
// 0x02 AlertLevel.fatal
// 0x70 AlertDescription.unrecognized_name (112, RFC 6066)
const TLS_ALERT_UNRECOGNIZED_NAME: [u8; 7] =
[0x15, 0x03, 0x03, 0x00, 0x02, 0x02, 0x70];
if let Err(e) = writer.write_all(&TLS_ALERT_UNRECOGNIZED_NAME).await {
debug!(
peer = %peer,
error = %e,
"Failed to write unrecognized_name TLS alert"
);
} else {
let _ = writer.flush().await;
}
}
return match action {
UnknownSniAction::Drop => HandshakeResult::Error(ProxyError::UnknownTlsSni),
UnknownSniAction::Drop | UnknownSniAction::RejectHandshake => {
HandshakeResult::Error(ProxyError::UnknownTlsSni)
}
UnknownSniAction::Mask => HandshakeResult::BadClient { reader, writer },
UnknownSniAction::Accept => unreachable!(),
};
@@ -1403,12 +1443,18 @@ where
let selected_domain =
matched_tls_domain.unwrap_or(config.censorship.tls_domain.as_str());
let cached_entry = cache.get(selected_domain).await;
let use_full_cert_payload = cache
.take_full_cert_budget_for_ip(
peer.ip(),
Duration::from_secs(config.censorship.tls_full_cert_ttl_secs),
)
.await;
let use_full_cert_payload = if config.censorship.serverhello_compact
&& matches!(client_tls_version, tls::ClientHelloTlsVersion::Tls12)
{
cache
.take_full_cert_budget_for_ip(
peer.ip(),
Duration::from_secs(config.censorship.tls_full_cert_ttl_secs),
)
.await
} else {
true
};
Some((cached_entry, use_full_cert_payload))
} else {
None
@@ -1429,6 +1475,8 @@ where
validation_session_id_slice,
&cached_entry,
use_full_cert_payload,
config.censorship.serverhello_compact,
client_tls_version,
rng,
selected_alpn.clone(),
config.censorship.tls_new_session_tickets,

View File

@@ -60,21 +60,18 @@ where
let mut buf = Box::new([0u8; MASK_BUFFER_SIZE]);
let mut total = 0usize;
let mut ended_by_eof = false;
if byte_cap == 0 {
return CopyOutcome {
total,
ended_by_eof,
};
}
let unlimited = byte_cap == 0;
loop {
let remaining_budget = byte_cap.saturating_sub(total);
if remaining_budget == 0 {
break;
}
let read_len = remaining_budget.min(MASK_BUFFER_SIZE);
let read_len = if unlimited {
MASK_BUFFER_SIZE
} else {
let remaining_budget = byte_cap.saturating_sub(total);
if remaining_budget == 0 {
break;
}
remaining_budget.min(MASK_BUFFER_SIZE)
};
let read_res = timeout(idle_timeout, reader.read(&mut buf[..read_len])).await;
let n = match read_res {
Ok(Ok(n)) => n,
@@ -930,21 +927,21 @@ async fn consume_client_data<R: AsyncRead + Unpin>(
byte_cap: usize,
idle_timeout: Duration,
) {
if byte_cap == 0 {
return;
}
// Keep drain path fail-closed under slow-loris stalls.
let mut buf = Box::new([0u8; MASK_BUFFER_SIZE]);
let mut total = 0usize;
let unlimited = byte_cap == 0;
loop {
let remaining_budget = byte_cap.saturating_sub(total);
if remaining_budget == 0 {
break;
}
let read_len = remaining_budget.min(MASK_BUFFER_SIZE);
let read_len = if unlimited {
MASK_BUFFER_SIZE
} else {
let remaining_budget = byte_cap.saturating_sub(total);
if remaining_budget == 0 {
break;
}
remaining_budget.min(MASK_BUFFER_SIZE)
};
let n = match timeout(idle_timeout, reader.read(&mut buf[..read_len])).await {
Ok(Ok(n)) => n,
Ok(Err(_)) | Err(_) => break,
@@ -955,7 +952,7 @@ async fn consume_client_data<R: AsyncRead + Unpin>(
}
total = total.saturating_add(n);
if total >= byte_cap {
if !unlimited && total >= byte_cap {
break;
}
}

View File

@@ -28,6 +28,7 @@ use crate::proxy::route_mode::{
use crate::proxy::shared_state::{
ConntrackCloseEvent, ConntrackClosePublishResult, ConntrackCloseReason, ProxySharedState,
};
use crate::proxy::traffic_limiter::{RateDirection, TrafficLease, next_refill_delay};
use crate::stats::{
MeD2cFlushReason, MeD2cQuotaRejectStage, MeD2cWriteMode, QuotaReserveError, Stats, UserStats,
};
@@ -286,6 +287,10 @@ impl RelayClientIdleState {
self.last_client_frame_at = now;
self.soft_idle_marked = false;
}
fn on_client_tiny_frame(&mut self, now: Instant) {
self.last_client_frame_at = now;
}
}
impl MeD2cFlushPolicy {
@@ -595,6 +600,41 @@ async fn reserve_user_quota_with_yield(
}
}
async fn wait_for_traffic_budget(
lease: Option<&Arc<TrafficLease>>,
direction: RateDirection,
bytes: u64,
) {
if bytes == 0 {
return;
}
let Some(lease) = lease else {
return;
};
let mut remaining = bytes;
while remaining > 0 {
let consume = lease.try_consume(direction, remaining);
if consume.granted > 0 {
remaining = remaining.saturating_sub(consume.granted);
continue;
}
let wait_started_at = Instant::now();
tokio::time::sleep(next_refill_delay()).await;
let wait_ms = wait_started_at
.elapsed()
.as_millis()
.min(u128::from(u64::MAX)) as u64;
lease.observe_wait_ms(
direction,
consume.blocked_user,
consume.blocked_cidr,
wait_ms,
);
}
}
fn classify_me_d2c_flush_reason(
flush_immediately: bool,
batch_frames: usize,
@@ -985,6 +1025,7 @@ where
let quota_limit = config.access.user_data_quota.get(&user).copied();
let quota_user_stats = quota_limit.map(|_| stats.get_or_create_user_stats_handle(&user));
let peer = success.peer;
let traffic_lease = shared.traffic_limiter.acquire_lease(&user, peer.ip());
let proto_tag = success.proto_tag;
let pool_generation = me_pool.current_generation();
@@ -1120,6 +1161,7 @@ where
let rng_clone = rng.clone();
let user_clone = user.clone();
let quota_user_stats_me_writer = quota_user_stats.clone();
let traffic_lease_me_writer = traffic_lease.clone();
let last_downstream_activity_ms_clone = last_downstream_activity_ms.clone();
let bytes_me2c_clone = bytes_me2c.clone();
let d2c_flush_policy = MeD2cFlushPolicy::from_config(&config);
@@ -1153,7 +1195,7 @@ where
let first_is_downstream_activity =
matches!(&first, MeResponse::Data { .. } | MeResponse::Ack(_));
match process_me_writer_response(
match process_me_writer_response_with_traffic_lease(
first,
&mut writer,
proto_tag,
@@ -1164,6 +1206,7 @@ where
quota_user_stats_me_writer.as_deref(),
quota_limit,
d2c_flush_policy.quota_soft_overshoot_bytes,
traffic_lease_me_writer.as_ref(),
bytes_me2c_clone.as_ref(),
conn_id,
d2c_flush_policy.ack_flush_immediate,
@@ -1213,7 +1256,7 @@ where
let next_is_downstream_activity =
matches!(&next, MeResponse::Data { .. } | MeResponse::Ack(_));
match process_me_writer_response(
match process_me_writer_response_with_traffic_lease(
next,
&mut writer,
proto_tag,
@@ -1224,6 +1267,7 @@ where
quota_user_stats_me_writer.as_deref(),
quota_limit,
d2c_flush_policy.quota_soft_overshoot_bytes,
traffic_lease_me_writer.as_ref(),
bytes_me2c_clone.as_ref(),
conn_id,
d2c_flush_policy.ack_flush_immediate,
@@ -1276,7 +1320,7 @@ where
Ok(Some(next)) => {
let next_is_downstream_activity =
matches!(&next, MeResponse::Data { .. } | MeResponse::Ack(_));
match process_me_writer_response(
match process_me_writer_response_with_traffic_lease(
next,
&mut writer,
proto_tag,
@@ -1287,6 +1331,7 @@ where
quota_user_stats_me_writer.as_deref(),
quota_limit,
d2c_flush_policy.quota_soft_overshoot_bytes,
traffic_lease_me_writer.as_ref(),
bytes_me2c_clone.as_ref(),
conn_id,
d2c_flush_policy.ack_flush_immediate,
@@ -1341,7 +1386,7 @@ where
let extra_is_downstream_activity =
matches!(&extra, MeResponse::Data { .. } | MeResponse::Ack(_));
match process_me_writer_response(
match process_me_writer_response_with_traffic_lease(
extra,
&mut writer,
proto_tag,
@@ -1352,6 +1397,7 @@ where
quota_user_stats_me_writer.as_deref(),
quota_limit,
d2c_flush_policy.quota_soft_overshoot_bytes,
traffic_lease_me_writer.as_ref(),
bytes_me2c_clone.as_ref(),
conn_id,
d2c_flush_policy.ack_flush_immediate,
@@ -1542,6 +1588,12 @@ where
match payload_result {
Ok(Some((payload, quickack))) => {
trace!(conn_id, bytes = payload.len(), "C->ME frame");
wait_for_traffic_budget(
traffic_lease.as_ref(),
RateDirection::Up,
payload.len() as u64,
)
.await;
forensics.bytes_c2me = forensics
.bytes_c2me
.saturating_add(payload.len() as u64);
@@ -1762,40 +1814,6 @@ where
let downstream_ms = last_downstream_activity_ms.load(Ordering::Relaxed);
let hard_deadline =
hard_deadline(idle_policy, idle_state, session_started_at, downstream_ms);
if now >= hard_deadline {
clear_relay_idle_candidate_in(shared, forensics.conn_id);
stats.increment_relay_idle_hard_close_total();
let client_idle_secs = now
.saturating_duration_since(idle_state.last_client_frame_at)
.as_secs();
let downstream_idle_secs = now
.saturating_duration_since(
session_started_at + Duration::from_millis(downstream_ms),
)
.as_secs();
warn!(
trace_id = format_args!("0x{:016x}", forensics.trace_id),
conn_id = forensics.conn_id,
user = %forensics.user,
read_label,
client_idle_secs,
downstream_idle_secs,
soft_idle_secs = idle_policy.soft_idle.as_secs(),
hard_idle_secs = idle_policy.hard_idle.as_secs(),
grace_secs = idle_policy.grace_after_downstream_activity.as_secs(),
"Middle-relay hard idle close"
);
return Err(ProxyError::Io(std::io::Error::new(
std::io::ErrorKind::TimedOut,
format!(
"middle-relay hard idle timeout while reading {read_label}: client_idle_secs={client_idle_secs}, downstream_idle_secs={downstream_idle_secs}, soft_idle_secs={}, hard_idle_secs={}, grace_secs={}",
idle_policy.soft_idle.as_secs(),
idle_policy.hard_idle.as_secs(),
idle_policy.grace_after_downstream_activity.as_secs(),
),
)));
}
if !idle_state.soft_idle_marked
&& now.saturating_duration_since(idle_state.last_client_frame_at)
>= idle_policy.soft_idle
@@ -1850,7 +1868,45 @@ where
),
)));
}
Err(_) => {}
Err(_) => {
let now = Instant::now();
let downstream_ms = last_downstream_activity_ms.load(Ordering::Relaxed);
let hard_deadline =
hard_deadline(idle_policy, idle_state, session_started_at, downstream_ms);
if now >= hard_deadline {
clear_relay_idle_candidate_in(shared, forensics.conn_id);
stats.increment_relay_idle_hard_close_total();
let client_idle_secs = now
.saturating_duration_since(idle_state.last_client_frame_at)
.as_secs();
let downstream_idle_secs = now
.saturating_duration_since(
session_started_at + Duration::from_millis(downstream_ms),
)
.as_secs();
warn!(
trace_id = format_args!("0x{:016x}", forensics.trace_id),
conn_id = forensics.conn_id,
user = %forensics.user,
read_label,
client_idle_secs,
downstream_idle_secs,
soft_idle_secs = idle_policy.soft_idle.as_secs(),
hard_idle_secs = idle_policy.hard_idle.as_secs(),
grace_secs = idle_policy.grace_after_downstream_activity.as_secs(),
"Middle-relay hard idle close"
);
return Err(ProxyError::Io(std::io::Error::new(
std::io::ErrorKind::TimedOut,
format!(
"middle-relay hard idle timeout while reading {read_label}: client_idle_secs={client_idle_secs}, downstream_idle_secs={downstream_idle_secs}, soft_idle_secs={}, hard_idle_secs={}, grace_secs={}",
idle_policy.soft_idle.as_secs(),
idle_policy.hard_idle.as_secs(),
idle_policy.grace_after_downstream_activity.as_secs(),
),
)));
}
}
}
}
@@ -1941,6 +1997,7 @@ where
};
if len == 0 {
idle_state.on_client_tiny_frame(Instant::now());
idle_state.tiny_frame_debt = idle_state
.tiny_frame_debt
.saturating_add(TINY_FRAME_DEBT_PER_TINY);
@@ -2144,6 +2201,7 @@ enum MeWriterResponseOutcome {
Close,
}
#[cfg(test)]
async fn process_me_writer_response<W>(
response: MeResponse,
client_writer: &mut CryptoWriter<W>,
@@ -2160,6 +2218,46 @@ async fn process_me_writer_response<W>(
ack_flush_immediate: bool,
batched: bool,
) -> Result<MeWriterResponseOutcome>
where
W: AsyncWrite + Unpin + Send + 'static,
{
process_me_writer_response_with_traffic_lease(
response,
client_writer,
proto_tag,
rng,
frame_buf,
stats,
user,
quota_user_stats,
quota_limit,
quota_soft_overshoot_bytes,
None,
bytes_me2c,
conn_id,
ack_flush_immediate,
batched,
)
.await
}
async fn process_me_writer_response_with_traffic_lease<W>(
response: MeResponse,
client_writer: &mut CryptoWriter<W>,
proto_tag: ProtoTag,
rng: &SecureRandom,
frame_buf: &mut Vec<u8>,
stats: &Stats,
user: &str,
quota_user_stats: Option<&UserStats>,
quota_limit: Option<u64>,
quota_soft_overshoot_bytes: u64,
traffic_lease: Option<&Arc<TrafficLease>>,
bytes_me2c: &AtomicU64,
conn_id: u64,
ack_flush_immediate: bool,
batched: bool,
) -> Result<MeWriterResponseOutcome>
where
W: AsyncWrite + Unpin + Send + 'static,
{
@@ -2183,6 +2281,7 @@ where
});
}
}
wait_for_traffic_budget(traffic_lease, RateDirection::Down, data_len).await;
let write_mode =
match write_client_payload(client_writer, proto_tag, flags, &data, rng, frame_buf)
@@ -2220,6 +2319,7 @@ where
} else {
trace!(conn_id, confirm, "ME->C quickack");
}
wait_for_traffic_budget(traffic_lease, RateDirection::Down, 4).await;
write_client_ack(client_writer, proto_tag, confirm).await?;
stats.increment_me_d2c_ack_frames_total();

View File

@@ -68,6 +68,7 @@ pub mod relay;
pub mod route_mode;
pub mod session_eviction;
pub mod shared_state;
pub mod traffic_limiter;
pub use client::ClientHandler;
#[allow(unused_imports)]

View File

@@ -52,6 +52,7 @@
//! - `SharedCounters` (atomics) let the watchdog read stats without locking
use crate::error::{ProxyError, Result};
use crate::proxy::traffic_limiter::{RateDirection, TrafficLease, next_refill_delay};
use crate::stats::{Stats, UserStats};
use crate::stream::BufferPool;
use std::io;
@@ -61,7 +62,7 @@ use std::sync::atomic::{AtomicBool, AtomicU64, Ordering};
use std::task::{Context, Poll};
use std::time::Duration;
use tokio::io::{AsyncRead, AsyncWrite, AsyncWriteExt, ReadBuf, copy_bidirectional_with_sizes};
use tokio::time::Instant;
use tokio::time::{Instant, Sleep};
use tracing::{debug, trace, warn};
// ============= Constants =============
@@ -210,13 +211,26 @@ struct StatsIo<S> {
stats: Arc<Stats>,
user: String,
user_stats: Arc<UserStats>,
traffic_lease: Option<Arc<TrafficLease>>,
c2s_rate_debt_bytes: u64,
c2s_wait: RateWaitState,
s2c_wait: RateWaitState,
quota_limit: Option<u64>,
quota_exceeded: Arc<AtomicBool>,
quota_bytes_since_check: u64,
epoch: Instant,
}
#[derive(Default)]
struct RateWaitState {
sleep: Option<Pin<Box<Sleep>>>,
started_at: Option<Instant>,
blocked_user: bool,
blocked_cidr: bool,
}
impl<S> StatsIo<S> {
#[cfg(test)]
fn new(
inner: S,
counters: Arc<SharedCounters>,
@@ -225,6 +239,28 @@ impl<S> StatsIo<S> {
quota_limit: Option<u64>,
quota_exceeded: Arc<AtomicBool>,
epoch: Instant,
) -> Self {
Self::new_with_traffic_lease(
inner,
counters,
stats,
user,
None,
quota_limit,
quota_exceeded,
epoch,
)
}
fn new_with_traffic_lease(
inner: S,
counters: Arc<SharedCounters>,
stats: Arc<Stats>,
user: String,
traffic_lease: Option<Arc<TrafficLease>>,
quota_limit: Option<u64>,
quota_exceeded: Arc<AtomicBool>,
epoch: Instant,
) -> Self {
// Mark initial activity so the watchdog doesn't fire before data flows
counters.touch(Instant::now(), epoch);
@@ -235,12 +271,88 @@ impl<S> StatsIo<S> {
stats,
user,
user_stats,
traffic_lease,
c2s_rate_debt_bytes: 0,
c2s_wait: RateWaitState::default(),
s2c_wait: RateWaitState::default(),
quota_limit,
quota_exceeded,
quota_bytes_since_check: 0,
epoch,
}
}
fn record_wait(
wait: &mut RateWaitState,
lease: Option<&Arc<TrafficLease>>,
direction: RateDirection,
) {
let Some(started_at) = wait.started_at.take() else {
return;
};
let wait_ms = started_at.elapsed().as_millis().min(u128::from(u64::MAX)) as u64;
if let Some(lease) = lease {
lease.observe_wait_ms(direction, wait.blocked_user, wait.blocked_cidr, wait_ms);
}
wait.blocked_user = false;
wait.blocked_cidr = false;
}
fn arm_wait(wait: &mut RateWaitState, blocked_user: bool, blocked_cidr: bool) {
if wait.sleep.is_none() {
wait.sleep = Some(Box::pin(tokio::time::sleep(next_refill_delay())));
wait.started_at = Some(Instant::now());
}
wait.blocked_user |= blocked_user;
wait.blocked_cidr |= blocked_cidr;
}
fn poll_wait(
wait: &mut RateWaitState,
cx: &mut Context<'_>,
lease: Option<&Arc<TrafficLease>>,
direction: RateDirection,
) -> Poll<()> {
let Some(sleep) = wait.sleep.as_mut() else {
return Poll::Ready(());
};
if sleep.as_mut().poll(cx).is_pending() {
return Poll::Pending;
}
wait.sleep = None;
Self::record_wait(wait, lease, direction);
Poll::Ready(())
}
fn settle_c2s_rate_debt(&mut self, cx: &mut Context<'_>) -> Poll<()> {
let Some(lease) = self.traffic_lease.as_ref() else {
self.c2s_rate_debt_bytes = 0;
return Poll::Ready(());
};
while self.c2s_rate_debt_bytes > 0 {
let consume = lease.try_consume(RateDirection::Up, self.c2s_rate_debt_bytes);
if consume.granted > 0 {
self.c2s_rate_debt_bytes = self.c2s_rate_debt_bytes.saturating_sub(consume.granted);
continue;
}
Self::arm_wait(
&mut self.c2s_wait,
consume.blocked_user,
consume.blocked_cidr,
);
if Self::poll_wait(&mut self.c2s_wait, cx, Some(lease), RateDirection::Up).is_pending()
{
return Poll::Pending;
}
}
if Self::poll_wait(&mut self.c2s_wait, cx, Some(lease), RateDirection::Up).is_pending() {
return Poll::Pending;
}
Poll::Ready(())
}
}
#[derive(Debug)]
@@ -286,6 +398,25 @@ fn should_immediate_quota_check(remaining_before: u64, charge_bytes: u64) -> boo
remaining_before <= QUOTA_NEAR_LIMIT_BYTES || charge_bytes >= QUOTA_LARGE_CHARGE_BYTES
}
fn refund_reserved_quota_bytes(user_stats: &UserStats, reserved_bytes: u64) {
if reserved_bytes == 0 {
return;
}
let mut current = user_stats.quota_used.load(Ordering::Relaxed);
loop {
let next = current.saturating_sub(reserved_bytes);
match user_stats.quota_used.compare_exchange_weak(
current,
next,
Ordering::Relaxed,
Ordering::Relaxed,
) {
Ok(_) => return,
Err(observed) => current = observed,
}
}
}
impl<S: AsyncRead + Unpin> AsyncRead for StatsIo<S> {
fn poll_read(
self: Pin<&mut Self>,
@@ -296,6 +427,9 @@ impl<S: AsyncRead + Unpin> AsyncRead for StatsIo<S> {
if this.quota_exceeded.load(Ordering::Acquire) {
return Poll::Ready(Err(quota_io_error()));
}
if this.settle_c2s_rate_debt(cx).is_pending() {
return Poll::Pending;
}
let mut remaining_before = None;
if let Some(limit) = this.quota_limit {
@@ -377,6 +511,11 @@ impl<S: AsyncRead + Unpin> AsyncRead for StatsIo<S> {
.add_user_octets_from_handle(this.user_stats.as_ref(), n_to_charge);
this.stats
.increment_user_msgs_from_handle(this.user_stats.as_ref());
if this.traffic_lease.is_some() {
this.c2s_rate_debt_bytes =
this.c2s_rate_debt_bytes.saturating_add(n_to_charge);
let _ = this.settle_c2s_rate_debt(cx);
}
trace!(user = %this.user, bytes = n, "C->S");
}
@@ -398,28 +537,66 @@ impl<S: AsyncWrite + Unpin> AsyncWrite for StatsIo<S> {
return Poll::Ready(Err(quota_io_error()));
}
let mut shaper_reserved_bytes = 0u64;
let mut write_buf = buf;
if let Some(lease) = this.traffic_lease.as_ref() {
if !buf.is_empty() {
loop {
let consume = lease.try_consume(RateDirection::Down, buf.len() as u64);
if consume.granted > 0 {
shaper_reserved_bytes = consume.granted;
if consume.granted < buf.len() as u64 {
write_buf = &buf[..consume.granted as usize];
}
let _ = Self::poll_wait(
&mut this.s2c_wait,
cx,
Some(lease),
RateDirection::Down,
);
break;
}
Self::arm_wait(
&mut this.s2c_wait,
consume.blocked_user,
consume.blocked_cidr,
);
if Self::poll_wait(&mut this.s2c_wait, cx, Some(lease), RateDirection::Down)
.is_pending()
{
return Poll::Pending;
}
}
} else {
let _ = Self::poll_wait(&mut this.s2c_wait, cx, Some(lease), RateDirection::Down);
}
}
let mut remaining_before = None;
let mut reserved_bytes = 0u64;
let mut write_buf = buf;
if let Some(limit) = this.quota_limit {
if !buf.is_empty() {
if !write_buf.is_empty() {
let mut reserve_rounds = 0usize;
while reserved_bytes == 0 {
let used_before = this.user_stats.quota_used();
let remaining = limit.saturating_sub(used_before);
if remaining == 0 {
if let Some(lease) = this.traffic_lease.as_ref() {
lease.refund(RateDirection::Down, shaper_reserved_bytes);
}
this.quota_exceeded.store(true, Ordering::Release);
return Poll::Ready(Err(quota_io_error()));
}
remaining_before = Some(remaining);
let desired = remaining.min(buf.len() as u64);
let desired = remaining.min(write_buf.len() as u64);
let mut saw_contention = false;
for _ in 0..QUOTA_RESERVE_SPIN_RETRIES {
match this.user_stats.quota_try_reserve(desired, limit) {
Ok(_) => {
reserved_bytes = desired;
write_buf = &buf[..desired as usize];
write_buf = &write_buf[..desired as usize];
break;
}
Err(crate::stats::QuotaReserveError::LimitExceeded) => {
@@ -434,6 +611,9 @@ impl<S: AsyncWrite + Unpin> AsyncWrite for StatsIo<S> {
if reserved_bytes == 0 {
reserve_rounds = reserve_rounds.saturating_add(1);
if reserve_rounds >= QUOTA_RESERVE_MAX_ROUNDS {
if let Some(lease) = this.traffic_lease.as_ref() {
lease.refund(RateDirection::Down, shaper_reserved_bytes);
}
this.quota_exceeded.store(true, Ordering::Release);
return Poll::Ready(Err(quota_io_error()));
}
@@ -446,6 +626,9 @@ impl<S: AsyncWrite + Unpin> AsyncWrite for StatsIo<S> {
let used_before = this.user_stats.quota_used();
let remaining = limit.saturating_sub(used_before);
if remaining == 0 {
if let Some(lease) = this.traffic_lease.as_ref() {
lease.refund(RateDirection::Down, shaper_reserved_bytes);
}
this.quota_exceeded.store(true, Ordering::Release);
return Poll::Ready(Err(quota_io_error()));
}
@@ -456,23 +639,20 @@ impl<S: AsyncWrite + Unpin> AsyncWrite for StatsIo<S> {
match Pin::new(&mut this.inner).poll_write(cx, write_buf) {
Poll::Ready(Ok(n)) => {
if reserved_bytes > n as u64 {
let refund = reserved_bytes - n as u64;
let mut current = this.user_stats.quota_used.load(Ordering::Relaxed);
loop {
let next = current.saturating_sub(refund);
match this.user_stats.quota_used.compare_exchange_weak(
current,
next,
Ordering::Relaxed,
Ordering::Relaxed,
) {
Ok(_) => break,
Err(observed) => current = observed,
}
}
refund_reserved_quota_bytes(
this.user_stats.as_ref(),
reserved_bytes - n as u64,
);
}
if shaper_reserved_bytes > n as u64
&& let Some(lease) = this.traffic_lease.as_ref()
{
lease.refund(RateDirection::Down, shaper_reserved_bytes - n as u64);
}
if n > 0 {
if let Some(lease) = this.traffic_lease.as_ref() {
Self::record_wait(&mut this.s2c_wait, Some(lease), RateDirection::Down);
}
let n_to_charge = n as u64;
// S→C: data written to client
@@ -512,37 +692,23 @@ impl<S: AsyncWrite + Unpin> AsyncWrite for StatsIo<S> {
}
Poll::Ready(Err(err)) => {
if reserved_bytes > 0 {
let mut current = this.user_stats.quota_used.load(Ordering::Relaxed);
loop {
let next = current.saturating_sub(reserved_bytes);
match this.user_stats.quota_used.compare_exchange_weak(
current,
next,
Ordering::Relaxed,
Ordering::Relaxed,
) {
Ok(_) => break,
Err(observed) => current = observed,
}
}
refund_reserved_quota_bytes(this.user_stats.as_ref(), reserved_bytes);
}
if shaper_reserved_bytes > 0
&& let Some(lease) = this.traffic_lease.as_ref()
{
lease.refund(RateDirection::Down, shaper_reserved_bytes);
}
Poll::Ready(Err(err))
}
Poll::Pending => {
if reserved_bytes > 0 {
let mut current = this.user_stats.quota_used.load(Ordering::Relaxed);
loop {
let next = current.saturating_sub(reserved_bytes);
match this.user_stats.quota_used.compare_exchange_weak(
current,
next,
Ordering::Relaxed,
Ordering::Relaxed,
) {
Ok(_) => break,
Err(observed) => current = observed,
}
}
refund_reserved_quota_bytes(this.user_stats.as_ref(), reserved_bytes);
}
if shaper_reserved_bytes > 0
&& let Some(lease) = this.traffic_lease.as_ref()
{
lease.refund(RateDirection::Down, shaper_reserved_bytes);
}
Poll::Pending
}
@@ -627,6 +793,43 @@ pub async fn relay_bidirectional_with_activity_timeout<CR, CW, SR, SW>(
_buffer_pool: Arc<BufferPool>,
activity_timeout: Duration,
) -> Result<()>
where
CR: AsyncRead + Unpin + Send + 'static,
CW: AsyncWrite + Unpin + Send + 'static,
SR: AsyncRead + Unpin + Send + 'static,
SW: AsyncWrite + Unpin + Send + 'static,
{
relay_bidirectional_with_activity_timeout_and_lease(
client_reader,
client_writer,
server_reader,
server_writer,
c2s_buf_size,
s2c_buf_size,
user,
stats,
quota_limit,
_buffer_pool,
None,
activity_timeout,
)
.await
}
pub async fn relay_bidirectional_with_activity_timeout_and_lease<CR, CW, SR, SW>(
client_reader: CR,
client_writer: CW,
server_reader: SR,
server_writer: SW,
c2s_buf_size: usize,
s2c_buf_size: usize,
user: &str,
stats: Arc<Stats>,
quota_limit: Option<u64>,
_buffer_pool: Arc<BufferPool>,
traffic_lease: Option<Arc<TrafficLease>>,
activity_timeout: Duration,
) -> Result<()>
where
CR: AsyncRead + Unpin + Send + 'static,
CW: AsyncWrite + Unpin + Send + 'static,
@@ -644,11 +847,12 @@ where
let mut server = CombinedStream::new(server_reader, server_writer);
// Wrap client with stats/activity tracking
let mut client = StatsIo::new(
let mut client = StatsIo::new_with_traffic_lease(
client_combined,
Arc::clone(&counters),
Arc::clone(&stats),
user_owned.clone(),
traffic_lease,
quota_limit,
Arc::clone(&quota_exceeded),
epoch,

View File

@@ -10,6 +10,7 @@ use tokio::sync::mpsc;
use crate::proxy::handshake::{AuthProbeSaturationState, AuthProbeState};
use crate::proxy::middle_relay::{DesyncDedupRotationState, RelayIdleCandidateRegistry};
use crate::proxy::traffic_limiter::TrafficLimiter;
const HANDSHAKE_RECENT_USER_RING_LEN: usize = 64;
@@ -65,6 +66,7 @@ pub(crate) struct MiddleRelaySharedState {
pub(crate) struct ProxySharedState {
pub(crate) handshake: HandshakeSharedState,
pub(crate) middle_relay: MiddleRelaySharedState,
pub(crate) traffic_limiter: Arc<TrafficLimiter>,
pub(crate) conntrack_pressure_active: AtomicBool,
pub(crate) conntrack_close_tx: Mutex<Option<mpsc::Sender<ConntrackCloseEvent>>>,
}
@@ -98,6 +100,7 @@ impl ProxySharedState {
relay_idle_registry: Mutex::new(RelayIdleCandidateRegistry::default()),
relay_idle_mark_seq: AtomicU64::new(0),
},
traffic_limiter: TrafficLimiter::new(),
conntrack_pressure_active: AtomicBool::new(false),
conntrack_close_tx: Mutex::new(None),
})

View File

@@ -2493,6 +2493,46 @@ fn unexpected_eof_is_classified_without_string_matching() {
);
}
#[test]
fn connection_reset_is_classified_as_expected_handshake_close() {
let beobachten = BeobachtenStore::new();
let mut config = ProxyConfig::default();
config.general.beobachten = true;
config.general.beobachten_minutes = 1;
let reset = ProxyError::Io(std::io::Error::from(std::io::ErrorKind::ConnectionReset));
let peer_ip: IpAddr = "198.51.100.202".parse().unwrap();
record_handshake_failure_class(&beobachten, &config, peer_ip, &reset);
let snapshot = beobachten.snapshot_text(Duration::from_secs(60));
assert!(
snapshot.contains("[expected_64_got_0]"),
"ConnectionReset must be classified as expected handshake close"
);
}
#[test]
fn stream_io_unexpected_eof_is_classified_without_string_matching() {
let beobachten = BeobachtenStore::new();
let mut config = ProxyConfig::default();
config.general.beobachten = true;
config.general.beobachten_minutes = 1;
let eof = ProxyError::Stream(StreamError::Io(std::io::Error::from(
std::io::ErrorKind::UnexpectedEof,
)));
let peer_ip: IpAddr = "198.51.100.203".parse().unwrap();
record_handshake_failure_class(&beobachten, &config, peer_ip, &eof);
let snapshot = beobachten.snapshot_text(Duration::from_secs(60));
assert!(
snapshot.contains("[expected_64_got_0]"),
"StreamError::Io(UnexpectedEof) must be classified as expected handshake close"
);
}
#[test]
fn non_eof_error_is_classified_as_other() {
let beobachten = BeobachtenStore::new();

View File

@@ -1007,6 +1007,55 @@ async fn tls_unknown_sni_mask_policy_falls_back_to_bad_client() {
assert!(matches!(result, HandshakeResult::BadClient { .. }));
}
#[tokio::test]
async fn tls_unknown_sni_reject_handshake_policy_emits_unrecognized_name_alert() {
use tokio::io::{AsyncReadExt, duplex};
let secret = [0x4Au8; 16];
let mut config = test_config_with_secret_hex("4a4a4a4a4a4a4a4a4a4a4a4a4a4a4a4a");
config.censorship.unknown_sni_action = UnknownSniAction::RejectHandshake;
let replay_checker = ReplayChecker::new(128, Duration::from_secs(60));
let rng = SecureRandom::new();
let peer: SocketAddr = "198.51.100.192:44326".parse().unwrap();
let handshake =
make_valid_tls_client_hello_with_sni_and_alpn(&secret, 0, "unknown.example", &[b"h2"]);
// Wire up a duplex so we can inspect what the server writes towards the
// client. We own the "peer side" half to read from it.
let (server_side, mut peer_side) = duplex(1024);
let (server_read, server_write) = tokio::io::split(server_side);
let result = handle_tls_handshake(
&handshake,
server_read,
server_write,
peer,
&config,
&replay_checker,
&rng,
None,
)
.await;
assert!(matches!(
result,
HandshakeResult::Error(ProxyError::UnknownTlsSni)
));
// Drain what the server wrote. We expect exactly one TLS alert record:
// 0x15 0x03 0x03 0x00 0x02 0x02 0x70
// (ContentType.alert, TLS 1.2, length=2, fatal, unrecognized_name)
drop(result); // drops the server-side writer so peer_side sees EOF
let mut buf = Vec::new();
peer_side.read_to_end(&mut buf).await.unwrap();
assert_eq!(
buf,
[0x15, 0x03, 0x03, 0x00, 0x02, 0x02, 0x70],
"reject_handshake must emit a fatal unrecognized_name TLS alert"
);
}
#[tokio::test]
async fn tls_unknown_sni_accept_policy_continues_auth_path() {
let secret = [0x4Bu8; 16];

View File

@@ -58,11 +58,22 @@ async fn consume_stall_stress_finishes_within_idle_budget() {
}
#[tokio::test]
async fn consume_zero_cap_returns_immediately() {
async fn consume_zero_cap_is_idle_bounded_on_stall() {
let started = Instant::now();
consume_client_data(tokio::io::empty(), 0, MASK_RELAY_IDLE_TIMEOUT).await;
tokio::time::timeout(
MASK_RELAY_TIMEOUT,
consume_client_data(OneByteThenStall { sent: false }, 0, MASK_RELAY_IDLE_TIMEOUT),
)
.await
.expect("zero-cap consume path must remain bounded by timeout guards");
let elapsed = started.elapsed();
assert!(
started.elapsed() < MASK_RELAY_IDLE_TIMEOUT,
"zero byte cap must return immediately"
elapsed >= (MASK_RELAY_IDLE_TIMEOUT / 2),
"zero cap must not short-circuit before idle timeout path, got {elapsed:?}"
);
assert!(
elapsed < MASK_RELAY_TIMEOUT,
"zero-cap consume path must complete before relay timeout, got {elapsed:?}"
);
}

View File

@@ -148,9 +148,10 @@ async fn positive_copy_with_production_cap_stops_exactly_at_budget() {
}
#[tokio::test]
async fn negative_consume_with_zero_cap_performs_no_reads() {
let read_calls = Arc::new(AtomicUsize::new(0));
let reader = FinitePatternReader::new(1024, 64, Arc::clone(&read_calls));
async fn consume_with_zero_cap_drains_until_eof() {
let payload = 256 * 1024;
let total_read = Arc::new(AtomicUsize::new(0));
let reader = BudgetProbeReader::new(payload, Arc::clone(&total_read));
consume_client_data_with_timeout_and_cap(
reader,
@@ -161,9 +162,27 @@ async fn negative_consume_with_zero_cap_performs_no_reads() {
.await;
assert_eq!(
read_calls.load(Ordering::Relaxed),
0,
"zero cap must return before reading attacker-controlled bytes"
total_read.load(Ordering::Relaxed),
payload,
"zero cap must disable byte budget and drain finite payload to EOF"
);
}
#[tokio::test]
async fn copy_with_zero_cap_drains_until_eof() {
let read_calls = Arc::new(AtomicUsize::new(0));
let payload = 73 * 1024;
let mut reader = FinitePatternReader::new(payload, 3072, read_calls);
let mut writer = CountingWriter::default();
let outcome =
copy_with_idle_timeout(&mut reader, &mut writer, 0, true, MASK_RELAY_IDLE_TIMEOUT).await;
assert_eq!(outcome.total, payload);
assert_eq!(writer.written, payload);
assert!(
outcome.ended_by_eof,
"zero cap must not terminate relay early on byte budget"
);
}

View File

@@ -0,0 +1,853 @@
use std::collections::{HashMap, HashSet};
use std::hash::{Hash, Hasher};
use std::net::IpAddr;
use std::sync::Arc;
use std::sync::OnceLock;
use std::sync::atomic::{AtomicU64, Ordering};
use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
use arc_swap::ArcSwap;
use dashmap::DashMap;
use ipnetwork::IpNetwork;
use crate::config::RateLimitBps;
const REGISTRY_SHARDS: usize = 64;
const FAIR_EPOCH_MS: u64 = 20;
const MAX_BORROW_CHUNK_BYTES: u64 = 32 * 1024;
const CLEANUP_INTERVAL_SECS: u64 = 60;
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum RateDirection {
Up,
Down,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct TrafficConsumeResult {
pub granted: u64,
pub blocked_user: bool,
pub blocked_cidr: bool,
}
#[derive(Debug, Clone, Copy)]
pub struct TrafficLimiterMetricsSnapshot {
pub user_throttle_up_total: u64,
pub user_throttle_down_total: u64,
pub cidr_throttle_up_total: u64,
pub cidr_throttle_down_total: u64,
pub user_wait_up_ms_total: u64,
pub user_wait_down_ms_total: u64,
pub cidr_wait_up_ms_total: u64,
pub cidr_wait_down_ms_total: u64,
pub user_active_leases: u64,
pub cidr_active_leases: u64,
pub user_policy_entries: u64,
pub cidr_policy_entries: u64,
}
#[derive(Default)]
struct ScopeMetrics {
throttle_up_total: AtomicU64,
throttle_down_total: AtomicU64,
wait_up_ms_total: AtomicU64,
wait_down_ms_total: AtomicU64,
active_leases: AtomicU64,
policy_entries: AtomicU64,
}
impl ScopeMetrics {
fn throttle(&self, direction: RateDirection) {
match direction {
RateDirection::Up => {
self.throttle_up_total.fetch_add(1, Ordering::Relaxed);
}
RateDirection::Down => {
self.throttle_down_total.fetch_add(1, Ordering::Relaxed);
}
}
}
fn wait_ms(&self, direction: RateDirection, wait_ms: u64) {
match direction {
RateDirection::Up => {
self.wait_up_ms_total.fetch_add(wait_ms, Ordering::Relaxed);
}
RateDirection::Down => {
self.wait_down_ms_total
.fetch_add(wait_ms, Ordering::Relaxed);
}
}
}
}
#[derive(Default)]
struct AtomicRatePair {
up_bps: AtomicU64,
down_bps: AtomicU64,
}
impl AtomicRatePair {
fn set(&self, limits: RateLimitBps) {
self.up_bps.store(limits.up_bps, Ordering::Relaxed);
self.down_bps.store(limits.down_bps, Ordering::Relaxed);
}
fn get(&self, direction: RateDirection) -> u64 {
match direction {
RateDirection::Up => self.up_bps.load(Ordering::Relaxed),
RateDirection::Down => self.down_bps.load(Ordering::Relaxed),
}
}
}
#[derive(Default)]
struct DirectionBucket {
epoch: AtomicU64,
used: AtomicU64,
}
impl DirectionBucket {
fn sync_epoch(&self, epoch: u64) {
let current = self.epoch.load(Ordering::Relaxed);
if current == epoch {
return;
}
if current < epoch
&& self
.epoch
.compare_exchange(current, epoch, Ordering::Relaxed, Ordering::Relaxed)
.is_ok()
{
self.used.store(0, Ordering::Relaxed);
}
}
fn try_consume(&self, cap_bps: u64, requested: u64) -> u64 {
if requested == 0 {
return 0;
}
if cap_bps == 0 {
return requested;
}
let epoch = current_epoch();
self.sync_epoch(epoch);
let cap_epoch = bytes_per_epoch(cap_bps);
loop {
let used = self.used.load(Ordering::Relaxed);
if used >= cap_epoch {
return 0;
}
let remaining = cap_epoch.saturating_sub(used);
let grant = requested.min(remaining);
if grant == 0 {
return 0;
}
let next = used.saturating_add(grant);
if self
.used
.compare_exchange_weak(used, next, Ordering::Relaxed, Ordering::Relaxed)
.is_ok()
{
return grant;
}
}
}
fn refund(&self, bytes: u64) {
if bytes == 0 {
return;
}
decrement_atomic_saturating(&self.used, bytes);
}
}
struct UserBucket {
rates: AtomicRatePair,
up: DirectionBucket,
down: DirectionBucket,
active_leases: AtomicU64,
}
impl UserBucket {
fn new(limits: RateLimitBps) -> Self {
let rates = AtomicRatePair::default();
rates.set(limits);
Self {
rates,
up: DirectionBucket::default(),
down: DirectionBucket::default(),
active_leases: AtomicU64::new(0),
}
}
fn set_rates(&self, limits: RateLimitBps) {
self.rates.set(limits);
}
fn try_consume(&self, direction: RateDirection, requested: u64) -> u64 {
let cap_bps = self.rates.get(direction);
match direction {
RateDirection::Up => self.up.try_consume(cap_bps, requested),
RateDirection::Down => self.down.try_consume(cap_bps, requested),
}
}
fn refund(&self, direction: RateDirection, bytes: u64) {
match direction {
RateDirection::Up => self.up.refund(bytes),
RateDirection::Down => self.down.refund(bytes),
}
}
}
#[derive(Default)]
struct CidrDirectionBucket {
epoch: AtomicU64,
used: AtomicU64,
active_users: AtomicU64,
}
impl CidrDirectionBucket {
fn sync_epoch(&self, epoch: u64) {
let current = self.epoch.load(Ordering::Relaxed);
if current == epoch {
return;
}
if current < epoch
&& self
.epoch
.compare_exchange(current, epoch, Ordering::Relaxed, Ordering::Relaxed)
.is_ok()
{
self.used.store(0, Ordering::Relaxed);
self.active_users.store(0, Ordering::Relaxed);
}
}
fn try_consume(
&self,
user_state: &CidrUserDirectionState,
cap_epoch: u64,
requested: u64,
) -> u64 {
if requested == 0 || cap_epoch == 0 {
return 0;
}
let epoch = current_epoch();
self.sync_epoch(epoch);
user_state.sync_epoch_and_mark_active(epoch, &self.active_users);
let active_users = self.active_users.load(Ordering::Relaxed).max(1);
let fair_share = cap_epoch.saturating_div(active_users).max(1);
loop {
let total_used = self.used.load(Ordering::Relaxed);
if total_used >= cap_epoch {
return 0;
}
let total_remaining = cap_epoch.saturating_sub(total_used);
let user_used = user_state.used.load(Ordering::Relaxed);
let guaranteed_remaining = fair_share.saturating_sub(user_used);
let grant = if guaranteed_remaining > 0 {
requested.min(guaranteed_remaining).min(total_remaining)
} else {
requested.min(total_remaining).min(MAX_BORROW_CHUNK_BYTES)
};
if grant == 0 {
return 0;
}
let next_total = total_used.saturating_add(grant);
if self
.used
.compare_exchange_weak(total_used, next_total, Ordering::Relaxed, Ordering::Relaxed)
.is_ok()
{
user_state.used.fetch_add(grant, Ordering::Relaxed);
return grant;
}
}
}
fn refund(&self, bytes: u64) {
if bytes == 0 {
return;
}
decrement_atomic_saturating(&self.used, bytes);
}
}
#[derive(Default)]
struct CidrUserDirectionState {
epoch: AtomicU64,
used: AtomicU64,
}
impl CidrUserDirectionState {
fn sync_epoch_and_mark_active(&self, epoch: u64, active_users: &AtomicU64) {
let current = self.epoch.load(Ordering::Relaxed);
if current == epoch {
return;
}
if current < epoch
&& self
.epoch
.compare_exchange(current, epoch, Ordering::Relaxed, Ordering::Relaxed)
.is_ok()
{
self.used.store(0, Ordering::Relaxed);
active_users.fetch_add(1, Ordering::Relaxed);
}
}
fn refund(&self, bytes: u64) {
if bytes == 0 {
return;
}
decrement_atomic_saturating(&self.used, bytes);
}
}
struct CidrUserShare {
active_conns: AtomicU64,
up: CidrUserDirectionState,
down: CidrUserDirectionState,
}
impl CidrUserShare {
fn new() -> Self {
Self {
active_conns: AtomicU64::new(0),
up: CidrUserDirectionState::default(),
down: CidrUserDirectionState::default(),
}
}
}
struct CidrBucket {
rates: AtomicRatePair,
up: CidrDirectionBucket,
down: CidrDirectionBucket,
users: ShardedRegistry<CidrUserShare>,
active_leases: AtomicU64,
}
impl CidrBucket {
fn new(limits: RateLimitBps) -> Self {
let rates = AtomicRatePair::default();
rates.set(limits);
Self {
rates,
up: CidrDirectionBucket::default(),
down: CidrDirectionBucket::default(),
users: ShardedRegistry::new(REGISTRY_SHARDS),
active_leases: AtomicU64::new(0),
}
}
fn set_rates(&self, limits: RateLimitBps) {
self.rates.set(limits);
}
fn acquire_user_share(&self, user: &str) -> Arc<CidrUserShare> {
let share = self.users.get_or_insert_with(user, CidrUserShare::new);
share.active_conns.fetch_add(1, Ordering::Relaxed);
share
}
fn release_user_share(&self, user: &str, share: &Arc<CidrUserShare>) {
decrement_atomic_saturating(&share.active_conns, 1);
let share_for_remove = Arc::clone(share);
let _ = self.users.remove_if(user, |candidate| {
Arc::ptr_eq(candidate, &share_for_remove)
&& candidate.active_conns.load(Ordering::Relaxed) == 0
});
}
fn try_consume_for_user(
&self,
direction: RateDirection,
share: &CidrUserShare,
requested: u64,
) -> u64 {
let cap_bps = self.rates.get(direction);
if cap_bps == 0 {
return requested;
}
let cap_epoch = bytes_per_epoch(cap_bps);
match direction {
RateDirection::Up => self.up.try_consume(&share.up, cap_epoch, requested),
RateDirection::Down => self.down.try_consume(&share.down, cap_epoch, requested),
}
}
fn refund_for_user(&self, direction: RateDirection, share: &CidrUserShare, bytes: u64) {
match direction {
RateDirection::Up => {
self.up.refund(bytes);
share.up.refund(bytes);
}
RateDirection::Down => {
self.down.refund(bytes);
share.down.refund(bytes);
}
}
}
fn cleanup_idle_users(&self) {
self.users
.retain(|_, share| share.active_conns.load(Ordering::Relaxed) > 0);
}
}
#[derive(Clone)]
struct CidrRule {
key: String,
cidr: IpNetwork,
limits: RateLimitBps,
prefix_len: u8,
}
#[derive(Default)]
struct PolicySnapshot {
user_limits: HashMap<String, RateLimitBps>,
cidr_rules_v4: Vec<CidrRule>,
cidr_rules_v6: Vec<CidrRule>,
cidr_rule_keys: HashSet<String>,
}
impl PolicySnapshot {
fn match_cidr(&self, ip: IpAddr) -> Option<&CidrRule> {
match ip {
IpAddr::V4(_) => self
.cidr_rules_v4
.iter()
.find(|rule| rule.cidr.contains(ip)),
IpAddr::V6(_) => self
.cidr_rules_v6
.iter()
.find(|rule| rule.cidr.contains(ip)),
}
}
}
struct ShardedRegistry<T> {
shards: Box<[DashMap<String, Arc<T>>]>,
mask: usize,
}
impl<T> ShardedRegistry<T> {
fn new(shards: usize) -> Self {
let shard_count = shards.max(1).next_power_of_two();
let mut items = Vec::with_capacity(shard_count);
for _ in 0..shard_count {
items.push(DashMap::<String, Arc<T>>::new());
}
Self {
shards: items.into_boxed_slice(),
mask: shard_count.saturating_sub(1),
}
}
fn shard_index(&self, key: &str) -> usize {
let mut hasher = std::collections::hash_map::DefaultHasher::new();
key.hash(&mut hasher);
(hasher.finish() as usize) & self.mask
}
fn get_or_insert_with<F>(&self, key: &str, make: F) -> Arc<T>
where
F: FnOnce() -> T,
{
let shard = &self.shards[self.shard_index(key)];
match shard.entry(key.to_string()) {
dashmap::mapref::entry::Entry::Occupied(entry) => Arc::clone(entry.get()),
dashmap::mapref::entry::Entry::Vacant(slot) => {
let value = Arc::new(make());
slot.insert(Arc::clone(&value));
value
}
}
}
fn retain<F>(&self, predicate: F)
where
F: Fn(&String, &Arc<T>) -> bool + Copy,
{
for shard in &*self.shards {
shard.retain(|key, value| predicate(key, value));
}
}
fn remove_if<F>(&self, key: &str, predicate: F) -> bool
where
F: Fn(&Arc<T>) -> bool,
{
let shard = &self.shards[self.shard_index(key)];
let should_remove = match shard.get(key) {
Some(entry) => predicate(entry.value()),
None => false,
};
if !should_remove {
return false;
}
shard.remove(key).is_some()
}
}
pub struct TrafficLease {
limiter: Arc<TrafficLimiter>,
user_bucket: Option<Arc<UserBucket>>,
cidr_bucket: Option<Arc<CidrBucket>>,
cidr_user_key: Option<String>,
cidr_user_share: Option<Arc<CidrUserShare>>,
}
impl TrafficLease {
pub fn try_consume(&self, direction: RateDirection, requested: u64) -> TrafficConsumeResult {
if requested == 0 {
return TrafficConsumeResult {
granted: 0,
blocked_user: false,
blocked_cidr: false,
};
}
let mut granted = requested;
if let Some(user_bucket) = self.user_bucket.as_ref() {
let user_granted = user_bucket.try_consume(direction, granted);
if user_granted == 0 {
self.limiter.observe_throttle(direction, true, false);
return TrafficConsumeResult {
granted: 0,
blocked_user: true,
blocked_cidr: false,
};
}
granted = user_granted;
}
if let (Some(cidr_bucket), Some(cidr_user_share)) =
(self.cidr_bucket.as_ref(), self.cidr_user_share.as_ref())
{
let cidr_granted =
cidr_bucket.try_consume_for_user(direction, cidr_user_share, granted);
if cidr_granted < granted
&& let Some(user_bucket) = self.user_bucket.as_ref()
{
user_bucket.refund(direction, granted.saturating_sub(cidr_granted));
}
if cidr_granted == 0 {
self.limiter.observe_throttle(direction, false, true);
return TrafficConsumeResult {
granted: 0,
blocked_user: false,
blocked_cidr: true,
};
}
granted = cidr_granted;
}
TrafficConsumeResult {
granted,
blocked_user: false,
blocked_cidr: false,
}
}
pub fn refund(&self, direction: RateDirection, bytes: u64) {
if bytes == 0 {
return;
}
if let Some(user_bucket) = self.user_bucket.as_ref() {
user_bucket.refund(direction, bytes);
}
if let (Some(cidr_bucket), Some(cidr_user_share)) =
(self.cidr_bucket.as_ref(), self.cidr_user_share.as_ref())
{
cidr_bucket.refund_for_user(direction, cidr_user_share, bytes);
}
}
pub fn observe_wait_ms(
&self,
direction: RateDirection,
blocked_user: bool,
blocked_cidr: bool,
wait_ms: u64,
) {
if wait_ms == 0 {
return;
}
self.limiter
.observe_wait(direction, blocked_user, blocked_cidr, wait_ms);
}
}
impl Drop for TrafficLease {
fn drop(&mut self) {
if let Some(bucket) = self.user_bucket.as_ref() {
decrement_atomic_saturating(&bucket.active_leases, 1);
decrement_atomic_saturating(&self.limiter.user_scope.active_leases, 1);
}
if let Some(bucket) = self.cidr_bucket.as_ref() {
if let (Some(user_key), Some(share)) =
(self.cidr_user_key.as_ref(), self.cidr_user_share.as_ref())
{
bucket.release_user_share(user_key, share);
}
decrement_atomic_saturating(&bucket.active_leases, 1);
decrement_atomic_saturating(&self.limiter.cidr_scope.active_leases, 1);
}
}
}
pub struct TrafficLimiter {
policy: ArcSwap<PolicySnapshot>,
user_buckets: ShardedRegistry<UserBucket>,
cidr_buckets: ShardedRegistry<CidrBucket>,
user_scope: ScopeMetrics,
cidr_scope: ScopeMetrics,
last_cleanup_epoch_secs: AtomicU64,
}
impl TrafficLimiter {
pub fn new() -> Arc<Self> {
Arc::new(Self {
policy: ArcSwap::from_pointee(PolicySnapshot::default()),
user_buckets: ShardedRegistry::new(REGISTRY_SHARDS),
cidr_buckets: ShardedRegistry::new(REGISTRY_SHARDS),
user_scope: ScopeMetrics::default(),
cidr_scope: ScopeMetrics::default(),
last_cleanup_epoch_secs: AtomicU64::new(0),
})
}
pub fn apply_policy(
&self,
user_limits: HashMap<String, RateLimitBps>,
cidr_limits: HashMap<IpNetwork, RateLimitBps>,
) {
let filtered_users = user_limits
.into_iter()
.filter(|(_, limit)| limit.up_bps > 0 || limit.down_bps > 0)
.collect::<HashMap<_, _>>();
let mut cidr_rules_v4 = Vec::new();
let mut cidr_rules_v6 = Vec::new();
let mut cidr_rule_keys = HashSet::new();
for (cidr, limits) in cidr_limits {
if limits.up_bps == 0 && limits.down_bps == 0 {
continue;
}
let key = cidr.to_string();
let rule = CidrRule {
key: key.clone(),
cidr,
limits,
prefix_len: cidr.prefix(),
};
cidr_rule_keys.insert(key);
match rule.cidr {
IpNetwork::V4(_) => cidr_rules_v4.push(rule),
IpNetwork::V6(_) => cidr_rules_v6.push(rule),
}
}
cidr_rules_v4.sort_by(|a, b| b.prefix_len.cmp(&a.prefix_len));
cidr_rules_v6.sort_by(|a, b| b.prefix_len.cmp(&a.prefix_len));
self.user_scope
.policy_entries
.store(filtered_users.len() as u64, Ordering::Relaxed);
self.cidr_scope
.policy_entries
.store(cidr_rule_keys.len() as u64, Ordering::Relaxed);
self.policy.store(Arc::new(PolicySnapshot {
user_limits: filtered_users,
cidr_rules_v4,
cidr_rules_v6,
cidr_rule_keys,
}));
self.maybe_cleanup();
}
pub fn acquire_lease(
self: &Arc<Self>,
user: &str,
client_ip: IpAddr,
) -> Option<Arc<TrafficLease>> {
let policy = self.policy.load_full();
let mut user_bucket = None;
if let Some(limit) = policy.user_limits.get(user).copied() {
let bucket = self
.user_buckets
.get_or_insert_with(user, || UserBucket::new(limit));
bucket.set_rates(limit);
bucket.active_leases.fetch_add(1, Ordering::Relaxed);
self.user_scope
.active_leases
.fetch_add(1, Ordering::Relaxed);
user_bucket = Some(bucket);
}
let mut cidr_bucket = None;
let mut cidr_user_key = None;
let mut cidr_user_share = None;
if let Some(rule) = policy.match_cidr(client_ip) {
let bucket = self
.cidr_buckets
.get_or_insert_with(rule.key.as_str(), || CidrBucket::new(rule.limits));
bucket.set_rates(rule.limits);
bucket.active_leases.fetch_add(1, Ordering::Relaxed);
self.cidr_scope
.active_leases
.fetch_add(1, Ordering::Relaxed);
let share = bucket.acquire_user_share(user);
cidr_user_key = Some(user.to_string());
cidr_user_share = Some(share);
cidr_bucket = Some(bucket);
}
if user_bucket.is_none() && cidr_bucket.is_none() {
return None;
}
self.maybe_cleanup();
Some(Arc::new(TrafficLease {
limiter: Arc::clone(self),
user_bucket,
cidr_bucket,
cidr_user_key,
cidr_user_share,
}))
}
pub fn metrics_snapshot(&self) -> TrafficLimiterMetricsSnapshot {
TrafficLimiterMetricsSnapshot {
user_throttle_up_total: self.user_scope.throttle_up_total.load(Ordering::Relaxed),
user_throttle_down_total: self.user_scope.throttle_down_total.load(Ordering::Relaxed),
cidr_throttle_up_total: self.cidr_scope.throttle_up_total.load(Ordering::Relaxed),
cidr_throttle_down_total: self.cidr_scope.throttle_down_total.load(Ordering::Relaxed),
user_wait_up_ms_total: self.user_scope.wait_up_ms_total.load(Ordering::Relaxed),
user_wait_down_ms_total: self.user_scope.wait_down_ms_total.load(Ordering::Relaxed),
cidr_wait_up_ms_total: self.cidr_scope.wait_up_ms_total.load(Ordering::Relaxed),
cidr_wait_down_ms_total: self.cidr_scope.wait_down_ms_total.load(Ordering::Relaxed),
user_active_leases: self.user_scope.active_leases.load(Ordering::Relaxed),
cidr_active_leases: self.cidr_scope.active_leases.load(Ordering::Relaxed),
user_policy_entries: self.user_scope.policy_entries.load(Ordering::Relaxed),
cidr_policy_entries: self.cidr_scope.policy_entries.load(Ordering::Relaxed),
}
}
fn observe_throttle(&self, direction: RateDirection, blocked_user: bool, blocked_cidr: bool) {
if blocked_user {
self.user_scope.throttle(direction);
}
if blocked_cidr {
self.cidr_scope.throttle(direction);
}
}
fn observe_wait(
&self,
direction: RateDirection,
blocked_user: bool,
blocked_cidr: bool,
wait_ms: u64,
) {
if blocked_user {
self.user_scope.wait_ms(direction, wait_ms);
}
if blocked_cidr {
self.cidr_scope.wait_ms(direction, wait_ms);
}
}
fn maybe_cleanup(&self) {
let now_epoch_secs = now_epoch_secs();
let last = self.last_cleanup_epoch_secs.load(Ordering::Relaxed);
if now_epoch_secs.saturating_sub(last) < CLEANUP_INTERVAL_SECS {
return;
}
if self
.last_cleanup_epoch_secs
.compare_exchange(last, now_epoch_secs, Ordering::Relaxed, Ordering::Relaxed)
.is_err()
{
return;
}
let policy = self.policy.load_full();
self.user_buckets.retain(|user, bucket| {
bucket.active_leases.load(Ordering::Relaxed) > 0
|| policy.user_limits.contains_key(user)
});
self.cidr_buckets.retain(|cidr_key, bucket| {
bucket.cleanup_idle_users();
bucket.active_leases.load(Ordering::Relaxed) > 0
|| policy.cidr_rule_keys.contains(cidr_key)
});
}
}
pub fn next_refill_delay() -> Duration {
let start = limiter_epoch_start();
let elapsed_ms = start.elapsed().as_millis() as u64;
let epoch_pos = elapsed_ms % FAIR_EPOCH_MS;
let wait_ms = FAIR_EPOCH_MS.saturating_sub(epoch_pos).max(1);
Duration::from_millis(wait_ms)
}
fn decrement_atomic_saturating(counter: &AtomicU64, by: u64) {
if by == 0 {
return;
}
let mut current = counter.load(Ordering::Relaxed);
loop {
if current == 0 {
return;
}
let next = current.saturating_sub(by);
match counter.compare_exchange_weak(current, next, Ordering::Relaxed, Ordering::Relaxed) {
Ok(_) => return,
Err(actual) => current = actual,
}
}
}
fn now_epoch_secs() -> u64 {
SystemTime::now()
.duration_since(UNIX_EPOCH)
.unwrap_or_default()
.as_secs()
}
fn bytes_per_epoch(bps: u64) -> u64 {
if bps == 0 {
return 0;
}
let numerator = bps.saturating_mul(FAIR_EPOCH_MS);
let bytes = numerator.saturating_div(8_000);
bytes.max(1)
}
fn current_epoch() -> u64 {
let start = limiter_epoch_start();
let elapsed_ms = start.elapsed().as_millis() as u64;
elapsed_ms / FAIR_EPOCH_MS
}
fn limiter_epoch_start() -> &'static Instant {
static START: OnceLock<Instant> = OnceLock::new();
START.get_or_init(Instant::now)
}

View File

@@ -88,6 +88,8 @@ impl Drop for RouteConnectionLease {
pub struct Stats {
connects_all: AtomicU64,
connects_bad: AtomicU64,
connects_bad_classes: DashMap<&'static str, AtomicU64>,
handshake_failure_classes: DashMap<&'static str, AtomicU64>,
current_connections_direct: AtomicU64,
current_connections_me: AtomicU64,
handshake_timeouts: AtomicU64,
@@ -175,6 +177,18 @@ pub struct Stats {
me_route_drop_queue_full: AtomicU64,
me_route_drop_queue_full_base: AtomicU64,
me_route_drop_queue_full_high: AtomicU64,
me_fair_pressure_state_gauge: AtomicU64,
me_fair_active_flows_gauge: AtomicU64,
me_fair_queued_bytes_gauge: AtomicU64,
me_fair_standing_flows_gauge: AtomicU64,
me_fair_backpressured_flows_gauge: AtomicU64,
me_fair_scheduler_rounds_total: AtomicU64,
me_fair_deficit_grants_total: AtomicU64,
me_fair_deficit_skips_total: AtomicU64,
me_fair_enqueue_rejects_total: AtomicU64,
me_fair_shed_drops_total: AtomicU64,
me_fair_penalties_total: AtomicU64,
me_fair_downstream_stalls_total: AtomicU64,
me_d2c_batches_total: AtomicU64,
me_d2c_batch_frames_total: AtomicU64,
me_d2c_batch_bytes_total: AtomicU64,
@@ -506,10 +520,32 @@ impl Stats {
self.connects_all.fetch_add(1, Ordering::Relaxed);
}
}
pub fn increment_connects_bad(&self) {
if self.telemetry_core_enabled() {
self.connects_bad.fetch_add(1, Ordering::Relaxed);
pub fn increment_connects_bad_with_class(&self, class: &'static str) {
if !self.telemetry_core_enabled() {
return;
}
self.connects_bad.fetch_add(1, Ordering::Relaxed);
let entry = self
.connects_bad_classes
.entry(class)
.or_insert_with(|| AtomicU64::new(0));
entry.fetch_add(1, Ordering::Relaxed);
}
pub fn increment_connects_bad(&self) {
self.increment_connects_bad_with_class("other");
}
pub fn increment_handshake_failure_class(&self, class: &'static str) {
if !self.telemetry_core_enabled() {
return;
}
let entry = self
.handshake_failure_classes
.entry(class)
.or_insert_with(|| AtomicU64::new(0));
entry.fetch_add(1, Ordering::Relaxed);
}
pub fn increment_current_connections_direct(&self) {
self.current_connections_direct
@@ -856,6 +892,78 @@ impl Stats {
.fetch_add(1, Ordering::Relaxed);
}
}
pub fn set_me_fair_pressure_state_gauge(&self, value: u64) {
if self.telemetry_me_allows_normal() {
self.me_fair_pressure_state_gauge
.store(value, Ordering::Relaxed);
}
}
pub fn set_me_fair_active_flows_gauge(&self, value: u64) {
if self.telemetry_me_allows_normal() {
self.me_fair_active_flows_gauge
.store(value, Ordering::Relaxed);
}
}
pub fn set_me_fair_queued_bytes_gauge(&self, value: u64) {
if self.telemetry_me_allows_normal() {
self.me_fair_queued_bytes_gauge
.store(value, Ordering::Relaxed);
}
}
pub fn set_me_fair_standing_flows_gauge(&self, value: u64) {
if self.telemetry_me_allows_normal() {
self.me_fair_standing_flows_gauge
.store(value, Ordering::Relaxed);
}
}
pub fn set_me_fair_backpressured_flows_gauge(&self, value: u64) {
if self.telemetry_me_allows_normal() {
self.me_fair_backpressured_flows_gauge
.store(value, Ordering::Relaxed);
}
}
pub fn add_me_fair_scheduler_rounds_total(&self, value: u64) {
if self.telemetry_me_allows_normal() && value > 0 {
self.me_fair_scheduler_rounds_total
.fetch_add(value, Ordering::Relaxed);
}
}
pub fn add_me_fair_deficit_grants_total(&self, value: u64) {
if self.telemetry_me_allows_normal() && value > 0 {
self.me_fair_deficit_grants_total
.fetch_add(value, Ordering::Relaxed);
}
}
pub fn add_me_fair_deficit_skips_total(&self, value: u64) {
if self.telemetry_me_allows_normal() && value > 0 {
self.me_fair_deficit_skips_total
.fetch_add(value, Ordering::Relaxed);
}
}
pub fn add_me_fair_enqueue_rejects_total(&self, value: u64) {
if self.telemetry_me_allows_normal() && value > 0 {
self.me_fair_enqueue_rejects_total
.fetch_add(value, Ordering::Relaxed);
}
}
pub fn add_me_fair_shed_drops_total(&self, value: u64) {
if self.telemetry_me_allows_normal() && value > 0 {
self.me_fair_shed_drops_total
.fetch_add(value, Ordering::Relaxed);
}
}
pub fn add_me_fair_penalties_total(&self, value: u64) {
if self.telemetry_me_allows_normal() && value > 0 {
self.me_fair_penalties_total
.fetch_add(value, Ordering::Relaxed);
}
}
pub fn add_me_fair_downstream_stalls_total(&self, value: u64) {
if self.telemetry_me_allows_normal() && value > 0 {
self.me_fair_downstream_stalls_total
.fetch_add(value, Ordering::Relaxed);
}
}
pub fn increment_me_d2c_batches_total(&self) {
if self.telemetry_me_allows_normal() {
self.me_d2c_batches_total.fetch_add(1, Ordering::Relaxed);
@@ -1556,6 +1664,37 @@ impl Stats {
pub fn get_connects_bad(&self) -> u64 {
self.connects_bad.load(Ordering::Relaxed)
}
pub fn get_connects_bad_class_counts(&self) -> Vec<(String, u64)> {
let mut out: Vec<(String, u64)> = self
.connects_bad_classes
.iter()
.map(|entry| {
(
entry.key().to_string(),
entry.value().load(Ordering::Relaxed),
)
})
.collect();
out.sort_by(|a, b| a.0.cmp(&b.0));
out
}
pub fn get_handshake_failure_class_counts(&self) -> Vec<(String, u64)> {
let mut out: Vec<(String, u64)> = self
.handshake_failure_classes
.iter()
.map(|entry| {
(
entry.key().to_string(),
entry.value().load(Ordering::Relaxed),
)
})
.collect();
out.sort_by(|a, b| a.0.cmp(&b.0));
out
}
pub fn get_accept_permit_timeout_total(&self) -> u64 {
self.accept_permit_timeout_total.load(Ordering::Relaxed)
}
@@ -1806,6 +1945,43 @@ impl Stats {
pub fn get_me_route_drop_queue_full_high(&self) -> u64 {
self.me_route_drop_queue_full_high.load(Ordering::Relaxed)
}
pub fn get_me_fair_pressure_state_gauge(&self) -> u64 {
self.me_fair_pressure_state_gauge.load(Ordering::Relaxed)
}
pub fn get_me_fair_active_flows_gauge(&self) -> u64 {
self.me_fair_active_flows_gauge.load(Ordering::Relaxed)
}
pub fn get_me_fair_queued_bytes_gauge(&self) -> u64 {
self.me_fair_queued_bytes_gauge.load(Ordering::Relaxed)
}
pub fn get_me_fair_standing_flows_gauge(&self) -> u64 {
self.me_fair_standing_flows_gauge.load(Ordering::Relaxed)
}
pub fn get_me_fair_backpressured_flows_gauge(&self) -> u64 {
self.me_fair_backpressured_flows_gauge
.load(Ordering::Relaxed)
}
pub fn get_me_fair_scheduler_rounds_total(&self) -> u64 {
self.me_fair_scheduler_rounds_total.load(Ordering::Relaxed)
}
pub fn get_me_fair_deficit_grants_total(&self) -> u64 {
self.me_fair_deficit_grants_total.load(Ordering::Relaxed)
}
pub fn get_me_fair_deficit_skips_total(&self) -> u64 {
self.me_fair_deficit_skips_total.load(Ordering::Relaxed)
}
pub fn get_me_fair_enqueue_rejects_total(&self) -> u64 {
self.me_fair_enqueue_rejects_total.load(Ordering::Relaxed)
}
pub fn get_me_fair_shed_drops_total(&self) -> u64 {
self.me_fair_shed_drops_total.load(Ordering::Relaxed)
}
pub fn get_me_fair_penalties_total(&self) -> u64 {
self.me_fair_penalties_total.load(Ordering::Relaxed)
}
pub fn get_me_fair_downstream_stalls_total(&self) -> u64 {
self.me_fair_downstream_stalls_total.load(Ordering::Relaxed)
}
pub fn get_me_d2c_batches_total(&self) -> u64 {
self.me_d2c_batches_total.load(Ordering::Relaxed)
}

View File

@@ -5,12 +5,15 @@ use crate::protocol::constants::{
MAX_TLS_CIPHERTEXT_SIZE, TLS_RECORD_APPLICATION, TLS_RECORD_CHANGE_CIPHER,
TLS_RECORD_HANDSHAKE, TLS_VERSION,
};
use crate::protocol::tls::{TLS_DIGEST_LEN, TLS_DIGEST_POS, gen_fake_x25519_key};
use crate::protocol::tls::{
ClientHelloTlsVersion, TLS_DIGEST_LEN, TLS_DIGEST_POS, gen_fake_x25519_key,
};
use crate::tls_front::types::{CachedTlsData, ParsedCertificateInfo, TlsProfileSource};
use crc32fast::Hasher;
const MIN_APP_DATA: usize = 64;
const MAX_APP_DATA: usize = MAX_TLS_CIPHERTEXT_SIZE;
const MAX_TICKET_RECORDS: usize = 4;
fn jitter_and_clamp_sizes(sizes: &[usize], rng: &SecureRandom) -> Vec<usize> {
sizes
@@ -62,6 +65,64 @@ fn ensure_payload_capacity(mut sizes: Vec<usize>, payload_len: usize) -> Vec<usi
sizes
}
fn emulated_app_data_sizes(cached: &CachedTlsData) -> Vec<usize> {
match cached.behavior_profile.source {
TlsProfileSource::Raw | TlsProfileSource::Merged => {
return cached
.app_data_records_sizes
.first()
.copied()
.or_else(|| {
cached
.behavior_profile
.app_data_record_sizes
.first()
.copied()
})
.map(|size| vec![size])
.unwrap_or_else(|| vec![cached.total_app_data_len.max(1024)]);
}
TlsProfileSource::Default | TlsProfileSource::Rustls => {}
}
let mut sizes = cached.app_data_records_sizes.clone();
if sizes.is_empty() {
sizes.push(cached.total_app_data_len.max(1024));
}
sizes
}
fn emulated_change_cipher_spec_count(_cached: &CachedTlsData) -> usize {
1
}
fn emulated_ticket_record_sizes(
cached: &CachedTlsData,
new_session_tickets: u8,
rng: &SecureRandom,
) -> Vec<usize> {
let target_count = usize::from(new_session_tickets.min(MAX_TICKET_RECORDS as u8));
if target_count == 0 {
return Vec::new();
}
let profiled_sizes = match cached.behavior_profile.source {
TlsProfileSource::Raw | TlsProfileSource::Merged => {
cached.behavior_profile.ticket_record_sizes.as_slice()
}
TlsProfileSource::Default | TlsProfileSource::Rustls => &[],
};
let mut sizes = Vec::with_capacity(target_count);
sizes.extend(profiled_sizes.iter().copied().take(target_count));
while sizes.len() < target_count {
sizes.push(rng.range(48) + 48);
}
sizes
}
fn build_compact_cert_info_payload(cert_info: &ParsedCertificateInfo) -> Option<Vec<u8>> {
let mut fields = Vec::new();
@@ -131,6 +192,8 @@ pub fn build_emulated_server_hello(
session_id: &[u8],
cached: &CachedTlsData,
use_full_cert_payload: bool,
serverhello_compact: bool,
client_tls_version: ClientHelloTlsVersion,
rng: &SecureRandom,
alpn: Option<Vec<u8>>,
new_session_tickets: u8,
@@ -180,53 +243,59 @@ pub fn build_emulated_server_hello(
server_hello.extend_from_slice(&message);
// --- ChangeCipherSpec ---
let change_cipher_spec = [
TLS_RECORD_CHANGE_CIPHER,
TLS_VERSION[0],
TLS_VERSION[1],
0x00,
0x01,
0x01,
];
let change_cipher_spec_count = emulated_change_cipher_spec_count(cached);
let mut change_cipher_spec = Vec::with_capacity(change_cipher_spec_count * 6);
for _ in 0..change_cipher_spec_count {
change_cipher_spec.extend_from_slice(&[
TLS_RECORD_CHANGE_CIPHER,
TLS_VERSION[0],
TLS_VERSION[1],
0x00,
0x01,
0x01,
]);
}
// --- ApplicationData (fake encrypted records) ---
let sizes = match cached.behavior_profile.source {
TlsProfileSource::Raw | TlsProfileSource::Merged => cached
.app_data_records_sizes
.first()
.copied()
.or_else(|| {
cached
.behavior_profile
.app_data_record_sizes
.first()
.copied()
})
.map(|size| vec![size])
.unwrap_or_else(|| vec![cached.total_app_data_len.max(1024)]),
_ => {
let mut sizes = cached.app_data_records_sizes.clone();
if sizes.is_empty() {
sizes.push(cached.total_app_data_len.max(1024));
let mut sizes = {
let base_sizes = emulated_app_data_sizes(cached);
match cached.behavior_profile.source {
TlsProfileSource::Raw | TlsProfileSource::Merged => base_sizes
.into_iter()
.map(|size| size.clamp(MIN_APP_DATA, MAX_APP_DATA))
.collect(),
TlsProfileSource::Default | TlsProfileSource::Rustls => {
jitter_and_clamp_sizes(&base_sizes, rng)
}
sizes
}
};
let mut sizes = jitter_and_clamp_sizes(&sizes, rng);
let compact_payload = cached
.cert_info
.as_ref()
.and_then(build_compact_cert_info_payload)
.and_then(hash_compact_cert_info_payload);
let selected_payload: Option<&[u8]> = if use_full_cert_payload {
let compact_payload = if serverhello_compact {
cached
.cert_payload
.cert_info
.as_ref()
.map(|payload| payload.certificate_message.as_slice())
.filter(|payload| !payload.is_empty())
.or(compact_payload.as_deref())
.and_then(build_compact_cert_info_payload)
.and_then(hash_compact_cert_info_payload)
} else {
compact_payload.as_deref()
None
};
let full_payload = cached
.cert_payload
.as_ref()
.map(|payload| payload.certificate_message.as_slice())
.filter(|payload| !payload.is_empty());
let selected_payload: Option<&[u8]> = match client_tls_version {
ClientHelloTlsVersion::Tls13 => None,
ClientHelloTlsVersion::Tls12 => {
if serverhello_compact {
if use_full_cert_payload {
full_payload.or(compact_payload.as_deref())
} else {
compact_payload.as_deref()
}
} else {
full_payload
}
}
};
if let Some(payload) = selected_payload {
@@ -299,17 +368,13 @@ pub fn build_emulated_server_hello(
// --- Combine ---
// Optional NewSessionTicket mimic records (opaque ApplicationData for fingerprint).
let mut tickets = Vec::new();
let ticket_count = new_session_tickets.min(4);
if ticket_count > 0 {
for _ in 0..ticket_count {
let ticket_len: usize = rng.range(48) + 48;
let mut rec = Vec::with_capacity(5 + ticket_len);
rec.push(TLS_RECORD_APPLICATION);
rec.extend_from_slice(&TLS_VERSION);
rec.extend_from_slice(&(ticket_len as u16).to_be_bytes());
rec.extend_from_slice(&rng.bytes(ticket_len));
tickets.extend_from_slice(&rec);
}
for ticket_len in emulated_ticket_record_sizes(cached, new_session_tickets, rng) {
let mut rec = Vec::with_capacity(5 + ticket_len);
rec.push(TLS_RECORD_APPLICATION);
rec.extend_from_slice(&TLS_VERSION);
rec.extend_from_slice(&(ticket_len as u16).to_be_bytes());
rec.extend_from_slice(&rng.bytes(ticket_len));
tickets.extend_from_slice(&rec);
}
let mut response = Vec::with_capacity(
@@ -334,6 +399,10 @@ pub fn build_emulated_server_hello(
#[path = "tests/emulator_security_tests.rs"]
mod security_tests;
#[cfg(test)]
#[path = "tests/emulator_profile_fidelity_security_tests.rs"]
mod emulator_profile_fidelity_security_tests;
#[cfg(test)]
mod tests {
use std::time::SystemTime;
@@ -350,6 +419,7 @@ mod tests {
use crate::protocol::constants::{
TLS_RECORD_APPLICATION, TLS_RECORD_CHANGE_CIPHER, TLS_RECORD_HANDSHAKE,
};
use crate::protocol::tls::ClientHelloTlsVersion;
fn first_app_data_payload(response: &[u8]) -> &[u8] {
let hello_len = u16::from_be_bytes([response[3], response[4]]) as usize;
@@ -396,6 +466,8 @@ mod tests {
&[0x22; 16],
&cached,
true,
true,
ClientHelloTlsVersion::Tls12,
&rng,
None,
0,
@@ -422,6 +494,8 @@ mod tests {
&[0x33; 16],
&cached,
true,
true,
ClientHelloTlsVersion::Tls12,
&rng,
None,
0,
@@ -454,6 +528,8 @@ mod tests {
&[0x55; 16],
&cached,
false,
true,
ClientHelloTlsVersion::Tls12,
&rng,
None,
0,
@@ -478,7 +554,69 @@ mod tests {
}
#[test]
fn test_build_emulated_server_hello_ignores_tail_records_for_raw_profile() {
fn test_build_emulated_server_hello_tls13_never_uses_cert_payload() {
let cert_msg = vec![0x0b, 0x00, 0x00, 0x05, 0x00, 0xaa, 0xbb, 0xcc, 0xdd];
let cached = make_cached(Some(TlsCertPayload {
cert_chain_der: vec![vec![0x30, 0x01, 0x00]],
certificate_message: cert_msg.clone(),
}));
let rng = SecureRandom::new();
let response = build_emulated_server_hello(
b"secret",
&[0x56; 32],
&[0x78; 16],
&cached,
true,
true,
ClientHelloTlsVersion::Tls13,
&rng,
None,
0,
);
let payload = first_app_data_payload(&response);
assert!(
!payload.starts_with(&cert_msg),
"TLS 1.3 response path must not expose certificate payload bytes"
);
}
#[test]
fn test_build_emulated_server_hello_compact_disabled_skips_compact_payload() {
let mut cached = make_cached(None);
cached.cert_info = Some(crate::tls_front::types::ParsedCertificateInfo {
not_after_unix: Some(1_900_000_000),
not_before_unix: Some(1_700_000_000),
issuer_cn: Some("Issuer".to_string()),
subject_cn: Some("example.com".to_string()),
san_names: vec!["example.com".to_string()],
});
let rng = SecureRandom::new();
let response = build_emulated_server_hello(
b"secret",
&[0x90; 32],
&[0x91; 16],
&cached,
false,
false,
ClientHelloTlsVersion::Tls12,
&rng,
Some(b"h2".to_vec()),
0,
);
let payload = first_app_data_payload(&response);
let expected_alpn_marker = [0x00u8, 0x10, 0x00, 0x05, 0x00, 0x03, 0x02, b'h', b'2'];
assert!(
payload.starts_with(&expected_alpn_marker),
"when compact mode is disabled and no full cert payload exists, the random/alpn path must be used"
);
}
#[test]
fn test_build_emulated_server_hello_ignores_tail_records_for_profiled_tls() {
let mut cached = make_cached(None);
cached.app_data_records_sizes = vec![27, 3905, 537, 69];
cached.total_app_data_len = 4538;
@@ -493,6 +631,8 @@ mod tests {
&[0x34; 16],
&cached,
false,
true,
ClientHelloTlsVersion::Tls13,
&rng,
None,
0,
@@ -503,8 +643,8 @@ mod tests {
let app_start = ccs_start + 6;
let app_len =
u16::from_be_bytes([response[app_start + 3], response[app_start + 4]]) as usize;
assert_eq!(response[app_start], TLS_RECORD_APPLICATION);
assert_eq!(app_len, 64);
assert_eq!(app_start + 5 + app_len, response.len());
}
}

View File

@@ -1,6 +1,7 @@
#![allow(clippy::too_many_arguments)]
use dashmap::DashMap;
use std::net::SocketAddr;
use std::sync::Arc;
use std::sync::OnceLock;
use std::time::{Duration, Instant};
@@ -19,6 +20,7 @@ use rustls::client::ClientConfig;
use rustls::client::danger::{HandshakeSignatureValid, ServerCertVerified, ServerCertVerifier};
use rustls::pki_types::{CertificateDer, ServerName, UnixTime};
use rustls::{DigitallySignedStruct, Error as RustlsError};
use x25519_dalek::{X25519_BASEPOINT_BYTES, x25519};
use x509_parser::certificate::X509Certificate;
use x509_parser::prelude::FromDer;
@@ -274,7 +276,7 @@ fn remember_profile_success(
);
}
fn build_client_config() -> Arc<ClientConfig> {
fn build_client_config(alpn_protocols: &[&[u8]]) -> Arc<ClientConfig> {
let root = rustls::RootCertStore::empty();
let provider = rustls::crypto::ring::default_provider();
@@ -287,6 +289,7 @@ fn build_client_config() -> Arc<ClientConfig> {
config
.dangerous()
.set_certificate_verifier(Arc::new(NoVerify));
config.alpn_protocols = alpn_protocols.iter().map(|proto| proto.to_vec()).collect();
Arc::new(config)
}
@@ -358,6 +361,22 @@ fn profile_alpn(profile: TlsFetchProfile) -> &'static [&'static [u8]] {
}
}
fn profile_alpn_labels(profile: TlsFetchProfile) -> &'static [&'static str] {
const H2_HTTP11: &[&str] = &["h2", "http/1.1"];
const HTTP11: &[&str] = &["http/1.1"];
match profile {
TlsFetchProfile::ModernChromeLike | TlsFetchProfile::ModernFirefoxLike => H2_HTTP11,
TlsFetchProfile::CompatTls12 | TlsFetchProfile::LegacyMinimal => HTTP11,
}
}
fn profile_session_id_len(profile: TlsFetchProfile) -> usize {
match profile {
TlsFetchProfile::ModernChromeLike | TlsFetchProfile::ModernFirefoxLike => 32,
TlsFetchProfile::CompatTls12 | TlsFetchProfile::LegacyMinimal => 0,
}
}
fn profile_supported_versions(profile: TlsFetchProfile) -> &'static [u16] {
const MODERN: &[u16] = &[0x0304, 0x0303];
const COMPAT: &[u16] = &[0x0303, 0x0304];
@@ -412,8 +431,20 @@ fn build_client_hello(
body.extend_from_slice(&rng.bytes(32));
}
// Session ID: empty
body.push(0);
// Use non-empty Session ID for modern TLS 1.3-like profiles to reduce middlebox friction.
let session_id_len = profile_session_id_len(profile);
let session_id = if session_id_len == 0 {
Vec::new()
} else if deterministic {
deterministic_bytes(
&format!("tls-fetch-session:{sni}:{}", profile.as_str()),
session_id_len,
)
} else {
rng.bytes(session_id_len)
};
body.push(session_id.len() as u8);
body.extend_from_slice(&session_id);
let mut cipher_suites = profile_cipher_suites(profile).to_vec();
if grease_enabled {
@@ -432,16 +463,26 @@ fn build_client_hello(
// === Extensions ===
let mut exts = Vec::new();
let mut push_extension = |ext_type: u16, data: &[u8]| {
exts.extend_from_slice(&ext_type.to_be_bytes());
exts.extend_from_slice(&(data.len() as u16).to_be_bytes());
exts.extend_from_slice(data);
};
// server_name (SNI)
let sni_bytes = sni.as_bytes();
let mut sni_ext = Vec::with_capacity(5 + sni_bytes.len());
sni_ext.extend_from_slice(&(sni_bytes.len() as u16 + 3).to_be_bytes());
sni_ext.push(0); // host_name
sni_ext.push(0);
sni_ext.extend_from_slice(&(sni_bytes.len() as u16).to_be_bytes());
sni_ext.extend_from_slice(sni_bytes);
exts.extend_from_slice(&0x0000u16.to_be_bytes());
exts.extend_from_slice(&(sni_ext.len() as u16).to_be_bytes());
exts.extend_from_slice(&sni_ext);
push_extension(0x0000, &sni_ext);
// Chrome-like profile keeps browser-like ordering and extension set.
if matches!(profile, TlsFetchProfile::ModernChromeLike) {
// ec_point_formats: uncompressed only.
push_extension(0x000b, &[0x01, 0x00]);
}
// supported_groups
let mut groups = profile_groups(profile).to_vec();
@@ -449,11 +490,16 @@ fn build_client_hello(
let grease = grease_value(rng, deterministic, &format!("group:{sni}"));
groups.insert(0, grease);
}
exts.extend_from_slice(&0x000au16.to_be_bytes());
exts.extend_from_slice(&((2 + groups.len() * 2) as u16).to_be_bytes());
exts.extend_from_slice(&(groups.len() as u16 * 2).to_be_bytes());
let mut groups_ext = Vec::with_capacity(2 + groups.len() * 2);
groups_ext.extend_from_slice(&(groups.len() as u16 * 2).to_be_bytes());
for g in groups {
exts.extend_from_slice(&g.to_be_bytes());
groups_ext.extend_from_slice(&g.to_be_bytes());
}
push_extension(0x000a, &groups_ext);
if matches!(profile, TlsFetchProfile::ModernChromeLike) {
// session_ticket
push_extension(0x0023, &[]);
}
// signature_algorithms
@@ -462,12 +508,12 @@ fn build_client_hello(
let grease = grease_value(rng, deterministic, &format!("sigalg:{sni}"));
sig_algs.insert(0, grease);
}
exts.extend_from_slice(&0x000du16.to_be_bytes());
exts.extend_from_slice(&((2 + sig_algs.len() * 2) as u16).to_be_bytes());
exts.extend_from_slice(&(sig_algs.len() as u16 * 2).to_be_bytes());
let mut sig_algs_ext = Vec::with_capacity(2 + sig_algs.len() * 2);
sig_algs_ext.extend_from_slice(&(sig_algs.len() as u16 * 2).to_be_bytes());
for a in sig_algs {
exts.extend_from_slice(&a.to_be_bytes());
sig_algs_ext.extend_from_slice(&a.to_be_bytes());
}
push_extension(0x000d, &sig_algs_ext);
// supported_versions
let mut versions = profile_supported_versions(profile).to_vec();
@@ -475,30 +521,32 @@ fn build_client_hello(
let grease = grease_value(rng, deterministic, &format!("version:{sni}"));
versions.insert(0, grease);
}
exts.extend_from_slice(&0x002bu16.to_be_bytes());
exts.extend_from_slice(&((1 + versions.len() * 2) as u16).to_be_bytes());
exts.push((versions.len() * 2) as u8);
let mut versions_ext = Vec::with_capacity(1 + versions.len() * 2);
versions_ext.push((versions.len() * 2) as u8);
for v in versions {
exts.extend_from_slice(&v.to_be_bytes());
versions_ext.extend_from_slice(&v.to_be_bytes());
}
push_extension(0x002b, &versions_ext);
if matches!(profile, TlsFetchProfile::ModernChromeLike) {
// psk_key_exchange_modes: psk_dhe_ke
push_extension(0x002d, &[0x01, 0x01]);
}
// key_share (x25519)
let key = if deterministic {
let det = deterministic_bytes(&format!("keyshare:{sni}"), 32);
let mut key = [0u8; 32];
key.copy_from_slice(&det);
key
} else {
gen_key_share(rng)
};
let key = gen_key_share(
rng,
deterministic,
&format!("tls-fetch-keyshare:{sni}:{}", profile.as_str()),
);
let mut keyshare = Vec::with_capacity(4 + key.len());
keyshare.extend_from_slice(&0x001du16.to_be_bytes()); // group
keyshare.extend_from_slice(&0x001du16.to_be_bytes());
keyshare.extend_from_slice(&(key.len() as u16).to_be_bytes());
keyshare.extend_from_slice(&key);
exts.extend_from_slice(&0x0033u16.to_be_bytes());
exts.extend_from_slice(&((2 + keyshare.len()) as u16).to_be_bytes());
exts.extend_from_slice(&(keyshare.len() as u16).to_be_bytes());
exts.extend_from_slice(&keyshare);
let mut keyshare_ext = Vec::with_capacity(2 + keyshare.len());
keyshare_ext.extend_from_slice(&(keyshare.len() as u16).to_be_bytes());
keyshare_ext.extend_from_slice(&keyshare);
push_extension(0x0033, &keyshare_ext);
// ALPN
let mut alpn_list = Vec::new();
@@ -507,16 +555,15 @@ fn build_client_hello(
alpn_list.extend_from_slice(proto);
}
if !alpn_list.is_empty() {
exts.extend_from_slice(&0x0010u16.to_be_bytes());
exts.extend_from_slice(&((2 + alpn_list.len()) as u16).to_be_bytes());
exts.extend_from_slice(&(alpn_list.len() as u16).to_be_bytes());
exts.extend_from_slice(&alpn_list);
let mut alpn_ext = Vec::with_capacity(2 + alpn_list.len());
alpn_ext.extend_from_slice(&(alpn_list.len() as u16).to_be_bytes());
alpn_ext.extend_from_slice(&alpn_list);
push_extension(0x0010, &alpn_ext);
}
if grease_enabled {
let grease = grease_value(rng, deterministic, &format!("ext:{sni}"));
exts.extend_from_slice(&grease.to_be_bytes());
exts.extend_from_slice(&0u16.to_be_bytes());
push_extension(grease, &[]);
}
// padding to reduce recognizability and keep length ~500 bytes
@@ -552,10 +599,14 @@ fn build_client_hello(
record
}
fn gen_key_share(rng: &SecureRandom) -> [u8; 32] {
let mut key = [0u8; 32];
key.copy_from_slice(&rng.bytes(32));
key
fn gen_key_share(rng: &SecureRandom, deterministic: bool, seed: &str) -> [u8; 32] {
let mut scalar = [0u8; 32];
if deterministic {
scalar.copy_from_slice(&deterministic_bytes(seed, 32));
} else {
scalar.copy_from_slice(&rng.bytes(32));
}
x25519(scalar, X25519_BASEPOINT_BYTES)
}
async fn read_tls_record<S>(stream: &mut S) -> Result<(u8, Vec<u8>)>
@@ -793,6 +844,51 @@ async fn connect_tcp_with_upstream(
))
}
fn socket_addrs_from_upstream_stream(
stream: &UpstreamStream,
) -> (Option<SocketAddr>, Option<SocketAddr>) {
match stream {
UpstreamStream::Tcp(tcp) => (tcp.local_addr().ok(), tcp.peer_addr().ok()),
UpstreamStream::Shadowsocks(_) => (None, None),
}
}
fn build_tls_fetch_proxy_header(
proxy_protocol: u8,
src_addr: Option<SocketAddr>,
dst_addr: Option<SocketAddr>,
) -> Option<Vec<u8>> {
match proxy_protocol {
0 => None,
2 => {
let header = match (src_addr, dst_addr) {
(Some(src @ SocketAddr::V4(_)), Some(dst @ SocketAddr::V4(_)))
| (Some(src @ SocketAddr::V6(_)), Some(dst @ SocketAddr::V6(_))) => {
ProxyProtocolV2Builder::new().with_addrs(src, dst).build()
}
_ => ProxyProtocolV2Builder::new().build(),
};
Some(header)
}
_ => {
let header = match (src_addr, dst_addr) {
(Some(SocketAddr::V4(src)), Some(SocketAddr::V4(dst))) => {
ProxyProtocolV1Builder::new()
.tcp4(src.into(), dst.into())
.build()
}
(Some(SocketAddr::V6(src)), Some(SocketAddr::V6(dst))) => {
ProxyProtocolV1Builder::new()
.tcp6(src.into(), dst.into())
.build()
}
_ => ProxyProtocolV1Builder::new().build(),
};
Some(header)
}
}
}
fn encode_tls13_certificate_message(cert_chain_der: &[Vec<u8>]) -> Option<Vec<u8>> {
if cert_chain_der.is_empty() {
return None;
@@ -824,7 +920,7 @@ async fn fetch_via_raw_tls_stream<S>(
mut stream: S,
sni: &str,
connect_timeout: Duration,
proxy_protocol: u8,
proxy_header: Option<Vec<u8>>,
profile: TlsFetchProfile,
grease_enabled: bool,
deterministic: bool,
@@ -835,11 +931,7 @@ where
let rng = SecureRandom::new();
let client_hello = build_client_hello(sni, &rng, profile, grease_enabled, deterministic);
timeout(connect_timeout, async {
if proxy_protocol > 0 {
let header = match proxy_protocol {
2 => ProxyProtocolV2Builder::new().build(),
_ => ProxyProtocolV1Builder::new().build(),
};
if let Some(header) = proxy_header.as_ref() {
stream.write_all(&header).await?;
}
stream.write_all(&client_hello).await?;
@@ -921,11 +1013,12 @@ async fn fetch_via_raw_tls(
sock = %sock_path,
"Raw TLS fetch using mask unix socket"
);
let proxy_header = build_tls_fetch_proxy_header(proxy_protocol, None, None);
return fetch_via_raw_tls_stream(
stream,
sni,
connect_timeout,
proxy_protocol,
proxy_header,
profile,
grease_enabled,
deterministic,
@@ -956,11 +1049,13 @@ async fn fetch_via_raw_tls(
let stream =
connect_tcp_with_upstream(host, port, connect_timeout, upstream, scope, strict_route)
.await?;
let (src_addr, dst_addr) = socket_addrs_from_upstream_stream(&stream);
let proxy_header = build_tls_fetch_proxy_header(proxy_protocol, src_addr, dst_addr);
fetch_via_raw_tls_stream(
stream,
sni,
connect_timeout,
proxy_protocol,
proxy_header,
profile,
grease_enabled,
deterministic,
@@ -972,22 +1067,19 @@ async fn fetch_via_rustls_stream<S>(
mut stream: S,
host: &str,
sni: &str,
proxy_protocol: u8,
proxy_header: Option<Vec<u8>>,
alpn_protocols: &[&[u8]],
) -> Result<TlsFetchResult>
where
S: AsyncRead + AsyncWrite + Unpin,
{
// rustls handshake path for certificate and basic negotiated metadata.
if proxy_protocol > 0 {
let header = match proxy_protocol {
2 => ProxyProtocolV2Builder::new().build(),
_ => ProxyProtocolV1Builder::new().build(),
};
if let Some(header) = proxy_header.as_ref() {
stream.write_all(&header).await?;
stream.flush().await?;
}
let config = build_client_config();
let config = build_client_config(alpn_protocols);
let connector = TlsConnector::from(config);
let server_name = ServerName::try_from(sni.to_owned())
@@ -1072,6 +1164,7 @@ async fn fetch_via_rustls(
proxy_protocol: u8,
unix_sock: Option<&str>,
strict_route: bool,
alpn_protocols: &[&[u8]],
) -> Result<TlsFetchResult> {
#[cfg(unix)]
if let Some(sock_path) = unix_sock {
@@ -1082,7 +1175,9 @@ async fn fetch_via_rustls(
sock = %sock_path,
"Rustls fetch using mask unix socket"
);
return fetch_via_rustls_stream(stream, host, sni, proxy_protocol).await;
let proxy_header = build_tls_fetch_proxy_header(proxy_protocol, None, None);
return fetch_via_rustls_stream(stream, host, sni, proxy_header, alpn_protocols)
.await;
}
Ok(Err(e)) => {
warn!(
@@ -1108,7 +1203,9 @@ async fn fetch_via_rustls(
let stream =
connect_tcp_with_upstream(host, port, connect_timeout, upstream, scope, strict_route)
.await?;
fetch_via_rustls_stream(stream, host, sni, proxy_protocol).await
let (src_addr, dst_addr) = socket_addrs_from_upstream_stream(&stream);
let proxy_header = build_tls_fetch_proxy_header(proxy_protocol, src_addr, dst_addr);
fetch_via_rustls_stream(stream, host, sni, proxy_header, alpn_protocols).await
}
/// Fetch real TLS metadata with an adaptive multi-profile strategy.
@@ -1147,6 +1244,14 @@ pub async fn fetch_real_tls_with_strategy(
break;
}
let timeout_for_attempt = attempt_timeout.min(total_budget - elapsed);
debug!(
sni = %sni,
profile = profile.as_str(),
alpn = ?profile_alpn_labels(profile),
grease_enabled = strategy.grease_enabled,
deterministic = strategy.deterministic,
"TLS fetch ClientHello params (raw)"
);
match fetch_via_raw_tls(
host,
@@ -1212,6 +1317,16 @@ pub async fn fetch_real_tls_with_strategy(
}
let rustls_timeout = attempt_timeout.min(total_budget - elapsed);
let rustls_profile = selected_profile.unwrap_or(TlsFetchProfile::ModernChromeLike);
let rustls_alpn_protocols = profile_alpn(rustls_profile);
debug!(
sni = %sni,
profile = rustls_profile.as_str(),
alpn = ?profile_alpn_labels(rustls_profile),
grease_enabled = strategy.grease_enabled,
deterministic = strategy.deterministic,
"TLS fetch ClientHello params (rustls)"
);
let rustls_result = fetch_via_rustls(
host,
port,
@@ -1222,6 +1337,7 @@ pub async fn fetch_real_tls_with_strategy(
proxy_protocol,
unix_sock,
strategy.strict_route,
rustls_alpn_protocols,
)
.await;
@@ -1278,11 +1394,13 @@ pub async fn fetch_real_tls(
#[cfg(test)]
mod tests {
use std::net::SocketAddr;
use std::time::{Duration, Instant};
use super::{
ProfileCacheValue, TlsFetchStrategy, build_client_hello, derive_behavior_profile,
encode_tls13_certificate_message, order_profiles, profile_cache, profile_cache_key,
ProfileCacheValue, TlsFetchStrategy, build_client_hello, build_tls_fetch_proxy_header,
derive_behavior_profile, encode_tls13_certificate_message, fetch_via_rustls_stream,
order_profiles, profile_alpn, profile_cache, profile_cache_key,
};
use crate::config::TlsFetchProfile;
use crate::crypto::SecureRandom;
@@ -1290,11 +1408,115 @@ mod tests {
TLS_RECORD_APPLICATION, TLS_RECORD_CHANGE_CIPHER, TLS_RECORD_HANDSHAKE,
};
use crate::tls_front::types::TlsProfileSource;
use tokio::io::AsyncReadExt;
struct ParsedClientHelloForTest {
session_id: Vec<u8>,
extensions: Vec<(u16, Vec<u8>)>,
}
fn read_u24(bytes: &[u8]) -> usize {
((bytes[0] as usize) << 16) | ((bytes[1] as usize) << 8) | (bytes[2] as usize)
}
fn parse_client_hello_for_test(record: &[u8]) -> ParsedClientHelloForTest {
assert!(record.len() >= 9, "record too short");
assert_eq!(record[0], TLS_RECORD_HANDSHAKE, "not a handshake record");
let record_len = u16::from_be_bytes([record[3], record[4]]) as usize;
assert_eq!(record.len(), 5 + record_len, "record length mismatch");
let handshake = &record[5..];
assert_eq!(handshake[0], 0x01, "not a ClientHello handshake");
let hello_len = read_u24(&handshake[1..4]);
assert_eq!(handshake.len(), 4 + hello_len, "handshake length mismatch");
let hello = &handshake[4..];
let mut pos = 0usize;
pos += 2;
pos += 32;
let session_len = hello[pos] as usize;
pos += 1;
let session_id = hello[pos..pos + session_len].to_vec();
pos += session_len;
let cipher_len = u16::from_be_bytes([hello[pos], hello[pos + 1]]) as usize;
pos += 2 + cipher_len;
let compression_len = hello[pos] as usize;
pos += 1 + compression_len;
let ext_len = u16::from_be_bytes([hello[pos], hello[pos + 1]]) as usize;
pos += 2;
let ext_end = pos + ext_len;
assert_eq!(ext_end, hello.len(), "extensions length mismatch");
let mut extensions = Vec::new();
while pos + 4 <= ext_end {
let ext_type = u16::from_be_bytes([hello[pos], hello[pos + 1]]);
let data_len = u16::from_be_bytes([hello[pos + 2], hello[pos + 3]]) as usize;
pos += 4;
let data = hello[pos..pos + data_len].to_vec();
pos += data_len;
extensions.push((ext_type, data));
}
assert_eq!(pos, ext_end, "extension parse did not consume all bytes");
ParsedClientHelloForTest {
session_id,
extensions,
}
}
fn parse_alpn_protocols(data: &[u8]) -> Vec<Vec<u8>> {
assert!(data.len() >= 2, "ALPN extension is too short");
let protocols_len = u16::from_be_bytes([data[0], data[1]]) as usize;
assert_eq!(protocols_len + 2, data.len(), "ALPN list length mismatch");
let mut pos = 2usize;
let mut out = Vec::new();
while pos < data.len() {
let len = data[pos] as usize;
pos += 1;
out.push(data[pos..pos + len].to_vec());
pos += len;
}
out
}
async fn capture_rustls_client_hello_record(
alpn_protocols: &'static [&'static [u8]],
) -> Vec<u8> {
let (client, mut server) = tokio::io::duplex(32 * 1024);
let fetch_task = tokio::spawn(async move {
fetch_via_rustls_stream(client, "example.com", "example.com", None, alpn_protocols)
.await
});
let mut header = [0u8; 5];
server
.read_exact(&mut header)
.await
.expect("must read client hello record header");
let body_len = u16::from_be_bytes([header[3], header[4]]) as usize;
let mut body = vec![0u8; body_len];
server
.read_exact(&mut body)
.await
.expect("must read client hello record body");
drop(server);
let result = fetch_task.await.expect("fetch task must join");
assert!(
result.is_err(),
"capture task should end with handshake error"
);
let mut record = Vec::with_capacity(5 + body_len);
record.extend_from_slice(&header);
record.extend_from_slice(&body);
record
}
#[test]
fn test_encode_tls13_certificate_message_single_cert() {
let cert = vec![0x30, 0x03, 0x02, 0x01, 0x01];
@@ -1423,4 +1645,228 @@ mod tests {
assert_eq!(first, second);
}
#[test]
fn test_raw_client_hello_alpn_matches_profile() {
let rng = SecureRandom::new();
for profile in [
TlsFetchProfile::ModernChromeLike,
TlsFetchProfile::ModernFirefoxLike,
TlsFetchProfile::CompatTls12,
TlsFetchProfile::LegacyMinimal,
] {
let hello = build_client_hello("alpn.example", &rng, profile, false, true);
let parsed = parse_client_hello_for_test(&hello);
let alpn_ext = parsed
.extensions
.iter()
.find(|(ext_type, _)| *ext_type == 0x0010)
.expect("ALPN extension must exist");
let parsed_alpn = parse_alpn_protocols(&alpn_ext.1);
let expected_alpn = profile_alpn(profile)
.iter()
.map(|proto| proto.to_vec())
.collect::<Vec<_>>();
assert_eq!(
parsed_alpn,
expected_alpn,
"ALPN mismatch for {}",
profile.as_str()
);
}
}
#[test]
fn test_modern_chrome_like_browser_extension_layout() {
let rng = SecureRandom::new();
let hello = build_client_hello(
"chrome.example",
&rng,
TlsFetchProfile::ModernChromeLike,
false,
true,
);
let parsed = parse_client_hello_for_test(&hello);
assert_eq!(
parsed.session_id.len(),
32,
"modern chrome must use non-empty session id"
);
let extension_ids = parsed
.extensions
.iter()
.map(|(ext_type, _)| *ext_type)
.collect::<Vec<_>>();
let expected_prefix = [
0x0000, 0x000b, 0x000a, 0x0023, 0x000d, 0x002b, 0x002d, 0x0033, 0x0010,
];
assert!(
extension_ids.as_slice().starts_with(&expected_prefix),
"unexpected extension order: {extension_ids:?}"
);
assert!(
extension_ids.contains(&0x0015),
"modern chrome profile should include padding extension"
);
let key_share = parsed
.extensions
.iter()
.find(|(ext_type, _)| *ext_type == 0x0033)
.expect("key_share extension must exist");
let key_share_data = &key_share.1;
assert!(
key_share_data.len() >= 2 + 4 + 32,
"key_share payload is too short"
);
let entry_len = u16::from_be_bytes([key_share_data[0], key_share_data[1]]) as usize;
assert_eq!(
entry_len,
key_share_data.len() - 2,
"key_share list length mismatch"
);
let group = u16::from_be_bytes([key_share_data[2], key_share_data[3]]);
let key_len = u16::from_be_bytes([key_share_data[4], key_share_data[5]]) as usize;
let key = &key_share_data[6..6 + key_len];
assert_eq!(group, 0x001d, "key_share group must be x25519");
assert_eq!(key_len, 32, "x25519 key length must be 32");
assert!(
key.iter().any(|b| *b != 0),
"x25519 key must not be all zero"
);
}
#[test]
fn test_fallback_profiles_keep_compat_extension_set() {
let rng = SecureRandom::new();
for profile in [
TlsFetchProfile::ModernFirefoxLike,
TlsFetchProfile::CompatTls12,
TlsFetchProfile::LegacyMinimal,
] {
let hello = build_client_hello("fallback.example", &rng, profile, false, true);
let parsed = parse_client_hello_for_test(&hello);
let extension_ids = parsed
.extensions
.iter()
.map(|(ext_type, _)| *ext_type)
.collect::<Vec<_>>();
assert!(extension_ids.contains(&0x0000), "SNI extension must exist");
assert!(
extension_ids.contains(&0x000a),
"supported_groups extension must exist"
);
assert!(
extension_ids.contains(&0x000d),
"signature_algorithms extension must exist"
);
assert!(
extension_ids.contains(&0x002b),
"supported_versions extension must exist"
);
assert!(
extension_ids.contains(&0x0033),
"key_share extension must exist"
);
assert!(extension_ids.contains(&0x0010), "ALPN extension must exist");
assert!(
!extension_ids.contains(&0x000b),
"ec_point_formats must stay chrome-only"
);
assert!(
!extension_ids.contains(&0x0023),
"session_ticket must stay chrome-only"
);
assert!(
!extension_ids.contains(&0x002d),
"psk_key_exchange_modes must stay chrome-only"
);
let expected_session_len = if matches!(profile, TlsFetchProfile::ModernFirefoxLike) {
32
} else {
0
};
assert_eq!(
parsed.session_id.len(),
expected_session_len,
"unexpected session id length for {}",
profile.as_str()
);
}
}
#[tokio::test(flavor = "current_thread")]
async fn test_rustls_client_hello_alpn_matches_selected_profile() {
for profile in [
TlsFetchProfile::ModernChromeLike,
TlsFetchProfile::CompatTls12,
TlsFetchProfile::LegacyMinimal,
] {
let record = capture_rustls_client_hello_record(profile_alpn(profile)).await;
let parsed = parse_client_hello_for_test(&record);
let alpn_ext = parsed
.extensions
.iter()
.find(|(ext_type, _)| *ext_type == 0x0010)
.expect("ALPN extension must exist");
let parsed_alpn = parse_alpn_protocols(&alpn_ext.1);
let expected_alpn = profile_alpn(profile)
.iter()
.map(|proto| proto.to_vec())
.collect::<Vec<_>>();
assert_eq!(
parsed_alpn,
expected_alpn,
"rustls ALPN mismatch for {}",
profile.as_str()
);
}
}
#[test]
fn test_build_tls_fetch_proxy_header_v2_with_tcp_addrs() {
let src: SocketAddr = "198.51.100.10:42000".parse().expect("valid src");
let dst: SocketAddr = "203.0.113.20:443".parse().expect("valid dst");
let header = build_tls_fetch_proxy_header(2, Some(src), Some(dst)).expect("header");
assert_eq!(
&header[..12],
&[
0x0d, 0x0a, 0x0d, 0x0a, 0x00, 0x0d, 0x0a, 0x51, 0x55, 0x49, 0x54, 0x0a
]
);
assert_eq!(header[12], 0x21);
assert_eq!(header[13], 0x11);
assert_eq!(u16::from_be_bytes([header[14], header[15]]), 12);
assert_eq!(&header[16..20], &[198, 51, 100, 10]);
assert_eq!(&header[20..24], &[203, 0, 113, 20]);
assert_eq!(u16::from_be_bytes([header[24], header[25]]), 42000);
assert_eq!(u16::from_be_bytes([header[26], header[27]]), 443);
}
#[test]
fn test_build_tls_fetch_proxy_header_v2_mixed_family_falls_back_to_local_command() {
let src: SocketAddr = "198.51.100.10:42000".parse().expect("valid src");
let dst: SocketAddr = "[2001:db8::20]:443".parse().expect("valid dst");
let header = build_tls_fetch_proxy_header(2, Some(src), Some(dst)).expect("header");
assert_eq!(header[12], 0x20);
assert_eq!(header[13], 0x00);
assert_eq!(u16::from_be_bytes([header[14], header[15]]), 0);
}
#[test]
fn test_build_tls_fetch_proxy_header_v1_with_tcp_addrs() {
let src: SocketAddr = "198.51.100.10:42000".parse().expect("valid src");
let dst: SocketAddr = "203.0.113.20:443".parse().expect("valid dst");
let header = build_tls_fetch_proxy_header(1, Some(src), Some(dst)).expect("header");
assert_eq!(
header,
b"PROXY TCP4 198.51.100.10 203.0.113.20 42000 443\r\n"
);
}
}

View File

@@ -0,0 +1,121 @@
use std::time::SystemTime;
use crate::crypto::SecureRandom;
use crate::protocol::constants::{
TLS_RECORD_APPLICATION, TLS_RECORD_CHANGE_CIPHER, TLS_RECORD_HANDSHAKE,
};
use crate::protocol::tls::ClientHelloTlsVersion;
use crate::tls_front::emulator::build_emulated_server_hello;
use crate::tls_front::types::{
CachedTlsData, ParsedServerHello, TlsBehaviorProfile, TlsProfileSource,
};
fn make_cached() -> CachedTlsData {
CachedTlsData {
server_hello_template: ParsedServerHello {
version: [0x03, 0x03],
random: [0u8; 32],
session_id: Vec::new(),
cipher_suite: [0x13, 0x01],
compression: 0,
extensions: Vec::new(),
},
cert_info: None,
cert_payload: None,
app_data_records_sizes: vec![1200, 900, 220, 180],
total_app_data_len: 2500,
behavior_profile: TlsBehaviorProfile {
change_cipher_spec_count: 2,
app_data_record_sizes: vec![1200, 900],
ticket_record_sizes: vec![220, 180],
source: TlsProfileSource::Merged,
},
fetched_at: SystemTime::now(),
domain: "example.com".to_string(),
}
}
fn record_lengths_by_type(response: &[u8], wanted_type: u8) -> Vec<usize> {
let mut out = Vec::new();
let mut pos = 0usize;
while pos + 5 <= response.len() {
let record_type = response[pos];
let record_len = u16::from_be_bytes([response[pos + 3], response[pos + 4]]) as usize;
if pos + 5 + record_len > response.len() {
break;
}
if record_type == wanted_type {
out.push(record_len);
}
pos += 5 + record_len;
}
out
}
#[test]
fn emulated_server_hello_keeps_single_change_cipher_spec_for_client_compatibility() {
let cached = make_cached();
let rng = SecureRandom::new();
let response = build_emulated_server_hello(
b"secret",
&[0x71; 32],
&[0x72; 16],
&cached,
false,
true,
ClientHelloTlsVersion::Tls13,
&rng,
None,
0,
);
assert_eq!(response[0], TLS_RECORD_HANDSHAKE);
let ccs_records = record_lengths_by_type(&response, TLS_RECORD_CHANGE_CIPHER);
assert_eq!(ccs_records.len(), 1);
assert!(ccs_records.iter().all(|len| *len == 1));
}
#[test]
fn emulated_server_hello_does_not_emit_profile_ticket_tail_when_disabled() {
let cached = make_cached();
let rng = SecureRandom::new();
let response = build_emulated_server_hello(
b"secret",
&[0x81; 32],
&[0x82; 16],
&cached,
false,
true,
ClientHelloTlsVersion::Tls13,
&rng,
None,
0,
);
let app_records = record_lengths_by_type(&response, TLS_RECORD_APPLICATION);
assert_eq!(app_records, vec![1200]);
}
#[test]
fn emulated_server_hello_uses_profile_ticket_lengths_when_enabled() {
let cached = make_cached();
let rng = SecureRandom::new();
let response = build_emulated_server_hello(
b"secret",
&[0x91; 32],
&[0x92; 16],
&cached,
false,
true,
ClientHelloTlsVersion::Tls13,
&rng,
None,
2,
);
let app_records = record_lengths_by_type(&response, TLS_RECORD_APPLICATION);
assert_eq!(app_records, vec![1200, 220, 180]);
}

View File

@@ -4,6 +4,7 @@ use crate::crypto::SecureRandom;
use crate::protocol::constants::{
TLS_RECORD_APPLICATION, TLS_RECORD_CHANGE_CIPHER, TLS_RECORD_HANDSHAKE,
};
use crate::protocol::tls::ClientHelloTlsVersion;
use crate::tls_front::emulator::build_emulated_server_hello;
use crate::tls_front::types::{
CachedTlsData, ParsedServerHello, TlsBehaviorProfile, TlsCertPayload, TlsProfileSource,
@@ -55,6 +56,8 @@ fn emulated_server_hello_ignores_oversized_alpn_when_marker_would_not_fit() {
&[0x22; 16],
&cached,
true,
true,
ClientHelloTlsVersion::Tls13,
&rng,
Some(oversized_alpn),
0,
@@ -91,6 +94,8 @@ fn emulated_server_hello_embeds_full_alpn_marker_when_body_can_fit() {
&[0x41; 16],
&cached,
true,
true,
ClientHelloTlsVersion::Tls13,
&rng,
Some(b"h2".to_vec()),
0,
@@ -119,6 +124,8 @@ fn emulated_server_hello_prefers_cert_payload_over_alpn_marker() {
&[0x42; 16],
&cached,
true,
true,
ClientHelloTlsVersion::Tls12,
&rng,
Some(b"h2".to_vec()),
0,

View File

@@ -321,7 +321,14 @@ async fn run_update_cycle(
let mut maps_changed = false;
let mut ready_v4: Option<(ProxyConfigData, u64)> = None;
let cfg_v4 = retry_fetch("https://core.telegram.org/getProxyConfig", upstream.clone()).await;
let cfg_v4 = retry_fetch(
cfg.general
.proxy_config_v4_url
.as_deref()
.unwrap_or("https://core.telegram.org/getProxyConfig"),
upstream.clone(),
)
.await;
if let Some(cfg_v4) = cfg_v4
&& snapshot_passes_guards(cfg, &cfg_v4, "getProxyConfig")
{
@@ -346,7 +353,10 @@ async fn run_update_cycle(
let mut ready_v6: Option<(ProxyConfigData, u64)> = None;
let cfg_v6 = retry_fetch(
"https://core.telegram.org/getProxyConfigV6",
cfg.general
.proxy_config_v6_url
.as_deref()
.unwrap_or("https://core.telegram.org/getProxyConfigV6"),
upstream.clone(),
)
.await;
@@ -430,6 +440,7 @@ async fn run_update_cycle(
match download_proxy_secret_with_max_len_via_upstream(
cfg.general.proxy_secret_len_max,
upstream,
cfg.general.proxy_secret_url.as_deref(),
)
.await
{

View File

@@ -0,0 +1,12 @@
//! Backpressure-driven fairness control for ME reader routing.
//!
//! This module keeps fairness decisions worker-local:
//! each reader loop owns one scheduler instance and mutates it without locks.
mod model;
mod pressure;
mod scheduler;
pub(crate) use model::PressureState;
pub(crate) use model::{AdmissionDecision, DispatchAction, DispatchFeedback, SchedulerDecision};
pub(crate) use scheduler::{WorkerFairnessConfig, WorkerFairnessSnapshot, WorkerFairnessState};

View File

@@ -0,0 +1,142 @@
use std::time::Instant;
use bytes::Bytes;
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
#[repr(u8)]
pub(crate) enum PressureState {
Normal = 0,
Pressured = 1,
Shedding = 2,
Saturated = 3,
}
impl PressureState {
pub(crate) fn as_u8(self) -> u8 {
self as u8
}
}
impl Default for PressureState {
fn default() -> Self {
Self::Normal
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(crate) enum FlowPressureClass {
Healthy,
Bursty,
Backpressured,
Standing,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(crate) enum StandingQueueState {
Transient,
Standing,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(crate) enum FlowSchedulerState {
Idle,
Active,
Backpressured,
Penalized,
SheddingCandidate,
}
#[derive(Debug, Clone)]
pub(crate) struct QueuedFrame {
pub(crate) conn_id: u64,
pub(crate) flags: u32,
pub(crate) data: Bytes,
pub(crate) enqueued_at: Instant,
}
impl QueuedFrame {
#[inline]
pub(crate) fn queued_bytes(&self) -> u64 {
self.data.len() as u64
}
}
#[derive(Debug, Clone)]
pub(crate) struct FlowFairnessState {
pub(crate) _flow_id: u64,
pub(crate) _worker_id: u16,
pub(crate) pending_bytes: u64,
pub(crate) deficit_bytes: i64,
pub(crate) queue_started_at: Option<Instant>,
pub(crate) last_drain_at: Option<Instant>,
pub(crate) recent_drain_bytes: u64,
pub(crate) consecutive_stalls: u8,
pub(crate) consecutive_skips: u8,
pub(crate) penalty_score: u16,
pub(crate) pressure_class: FlowPressureClass,
pub(crate) standing_state: StandingQueueState,
pub(crate) scheduler_state: FlowSchedulerState,
pub(crate) bucket_id: usize,
pub(crate) weight_quanta: u8,
pub(crate) in_active_ring: bool,
}
impl FlowFairnessState {
pub(crate) fn new(flow_id: u64, worker_id: u16, bucket_id: usize, weight_quanta: u8) -> Self {
Self {
_flow_id: flow_id,
_worker_id: worker_id,
pending_bytes: 0,
deficit_bytes: 0,
queue_started_at: None,
last_drain_at: None,
recent_drain_bytes: 0,
consecutive_stalls: 0,
consecutive_skips: 0,
penalty_score: 0,
pressure_class: FlowPressureClass::Healthy,
standing_state: StandingQueueState::Transient,
scheduler_state: FlowSchedulerState::Idle,
bucket_id,
weight_quanta: weight_quanta.max(1),
in_active_ring: false,
}
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(crate) enum AdmissionDecision {
Admit,
RejectWorkerCap,
RejectFlowCap,
RejectBucketCap,
RejectSaturated,
RejectStandingFlow,
}
#[derive(Debug, Clone)]
pub(crate) enum SchedulerDecision {
Idle,
Dispatch(DispatchCandidate),
}
#[derive(Debug, Clone)]
pub(crate) struct DispatchCandidate {
pub(crate) frame: QueuedFrame,
pub(crate) pressure_state: PressureState,
pub(crate) flow_class: FlowPressureClass,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(crate) enum DispatchFeedback {
Routed,
QueueFull,
ChannelClosed,
NoConn,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(crate) enum DispatchAction {
Continue,
CloseFlow,
}

View File

@@ -0,0 +1,227 @@
use std::time::{Duration, Instant};
use super::model::PressureState;
#[derive(Debug, Clone, Copy)]
pub(crate) struct PressureSignals {
pub(crate) active_flows: usize,
pub(crate) total_queued_bytes: u64,
pub(crate) standing_flows: usize,
pub(crate) backpressured_flows: usize,
}
#[derive(Debug, Clone)]
pub(crate) struct PressureConfig {
pub(crate) backpressure_enabled: bool,
pub(crate) evaluate_every_rounds: u32,
pub(crate) transition_hysteresis_rounds: u8,
pub(crate) standing_ratio_pressured_pct: u8,
pub(crate) standing_ratio_shedding_pct: u8,
pub(crate) standing_ratio_saturated_pct: u8,
pub(crate) queue_ratio_pressured_pct: u8,
pub(crate) queue_ratio_shedding_pct: u8,
pub(crate) queue_ratio_saturated_pct: u8,
pub(crate) reject_window: Duration,
pub(crate) rejects_pressured: u32,
pub(crate) rejects_shedding: u32,
pub(crate) rejects_saturated: u32,
pub(crate) stalls_pressured: u32,
pub(crate) stalls_shedding: u32,
pub(crate) stalls_saturated: u32,
}
impl Default for PressureConfig {
fn default() -> Self {
Self {
backpressure_enabled: true,
evaluate_every_rounds: 8,
transition_hysteresis_rounds: 3,
standing_ratio_pressured_pct: 20,
standing_ratio_shedding_pct: 35,
standing_ratio_saturated_pct: 50,
queue_ratio_pressured_pct: 65,
queue_ratio_shedding_pct: 82,
queue_ratio_saturated_pct: 94,
reject_window: Duration::from_secs(2),
rejects_pressured: 32,
rejects_shedding: 96,
rejects_saturated: 256,
stalls_pressured: 32,
stalls_shedding: 96,
stalls_saturated: 256,
}
}
}
#[derive(Debug)]
pub(crate) struct PressureEvaluator {
state: PressureState,
candidate_state: PressureState,
candidate_hits: u8,
rounds_since_eval: u32,
window_started_at: Instant,
admission_rejects_window: u32,
route_stalls_window: u32,
}
impl PressureEvaluator {
pub(crate) fn new(now: Instant) -> Self {
Self {
state: PressureState::Normal,
candidate_state: PressureState::Normal,
candidate_hits: 0,
rounds_since_eval: 0,
window_started_at: now,
admission_rejects_window: 0,
route_stalls_window: 0,
}
}
#[inline]
pub(crate) fn state(&self) -> PressureState {
self.state
}
pub(crate) fn note_admission_reject(&mut self, now: Instant, cfg: &PressureConfig) {
self.rotate_window_if_needed(now, cfg);
self.admission_rejects_window = self.admission_rejects_window.saturating_add(1);
}
pub(crate) fn note_route_stall(&mut self, now: Instant, cfg: &PressureConfig) {
self.rotate_window_if_needed(now, cfg);
self.route_stalls_window = self.route_stalls_window.saturating_add(1);
}
pub(crate) fn maybe_evaluate(
&mut self,
now: Instant,
cfg: &PressureConfig,
max_total_queued_bytes: u64,
signals: PressureSignals,
force: bool,
) -> PressureState {
self.rotate_window_if_needed(now, cfg);
if !cfg.backpressure_enabled {
self.state = PressureState::Normal;
self.candidate_state = PressureState::Normal;
self.candidate_hits = 0;
self.rounds_since_eval = 0;
return self.state;
}
self.rounds_since_eval = self.rounds_since_eval.saturating_add(1);
if !force && self.rounds_since_eval < cfg.evaluate_every_rounds.max(1) {
return self.state;
}
self.rounds_since_eval = 0;
let target = self.derive_target_state(cfg, max_total_queued_bytes, signals);
if target == self.state {
self.candidate_state = target;
self.candidate_hits = 0;
return self.state;
}
if self.candidate_state == target {
self.candidate_hits = self.candidate_hits.saturating_add(1);
} else {
self.candidate_state = target;
self.candidate_hits = 1;
}
if self.candidate_hits >= cfg.transition_hysteresis_rounds.max(1) {
self.state = target;
self.candidate_hits = 0;
}
self.state
}
fn derive_target_state(
&self,
cfg: &PressureConfig,
max_total_queued_bytes: u64,
signals: PressureSignals,
) -> PressureState {
if !cfg.backpressure_enabled {
return PressureState::Normal;
}
let queue_ratio_pct = if max_total_queued_bytes == 0 {
100
} else {
((signals.total_queued_bytes.saturating_mul(100)) / max_total_queued_bytes).min(100)
as u8
};
let standing_ratio_pct = if signals.active_flows == 0 {
0
} else {
((signals.standing_flows.saturating_mul(100)) / signals.active_flows).min(100) as u8
};
let mut pressure_score = 0u8;
if queue_ratio_pct >= cfg.queue_ratio_pressured_pct {
pressure_score = pressure_score.max(1);
}
if queue_ratio_pct >= cfg.queue_ratio_shedding_pct {
pressure_score = pressure_score.max(2);
}
if queue_ratio_pct >= cfg.queue_ratio_saturated_pct {
pressure_score = pressure_score.max(3);
}
if standing_ratio_pct >= cfg.standing_ratio_pressured_pct {
pressure_score = pressure_score.max(1);
}
if standing_ratio_pct >= cfg.standing_ratio_shedding_pct {
pressure_score = pressure_score.max(2);
}
if standing_ratio_pct >= cfg.standing_ratio_saturated_pct {
pressure_score = pressure_score.max(3);
}
if self.admission_rejects_window >= cfg.rejects_pressured {
pressure_score = pressure_score.max(1);
}
if self.admission_rejects_window >= cfg.rejects_shedding {
pressure_score = pressure_score.max(2);
}
if self.admission_rejects_window >= cfg.rejects_saturated {
pressure_score = pressure_score.max(3);
}
if self.route_stalls_window >= cfg.stalls_pressured {
pressure_score = pressure_score.max(1);
}
if self.route_stalls_window >= cfg.stalls_shedding {
pressure_score = pressure_score.max(2);
}
if self.route_stalls_window >= cfg.stalls_saturated {
pressure_score = pressure_score.max(3);
}
if signals.backpressured_flows > signals.active_flows.saturating_div(2)
&& signals.active_flows > 0
{
pressure_score = pressure_score.max(2);
}
match pressure_score {
0 => PressureState::Normal,
1 => PressureState::Pressured,
2 => PressureState::Shedding,
_ => PressureState::Saturated,
}
}
fn rotate_window_if_needed(&mut self, now: Instant, cfg: &PressureConfig) {
if now.saturating_duration_since(self.window_started_at) < cfg.reject_window {
return;
}
self.window_started_at = now;
self.admission_rejects_window = 0;
self.route_stalls_window = 0;
}
}

View File

@@ -0,0 +1,806 @@
use std::collections::{HashMap, HashSet, VecDeque};
use std::time::{Duration, Instant};
use crate::protocol::constants::RPC_FLAG_QUICKACK;
use bytes::Bytes;
use super::model::{
AdmissionDecision, DispatchAction, DispatchCandidate, DispatchFeedback, FlowFairnessState,
FlowPressureClass, FlowSchedulerState, PressureState, QueuedFrame, SchedulerDecision,
StandingQueueState,
};
use super::pressure::{PressureConfig, PressureEvaluator, PressureSignals};
#[derive(Debug, Clone)]
pub(crate) struct WorkerFairnessConfig {
pub(crate) worker_id: u16,
pub(crate) backpressure_enabled: bool,
pub(crate) max_active_flows: usize,
pub(crate) max_total_queued_bytes: u64,
pub(crate) max_flow_queued_bytes: u64,
pub(crate) base_quantum_bytes: u32,
pub(crate) pressured_quantum_bytes: u32,
pub(crate) penalized_quantum_bytes: u32,
pub(crate) standing_queue_min_age: Duration,
pub(crate) standing_queue_min_backlog_bytes: u64,
pub(crate) standing_stall_threshold: u8,
pub(crate) max_consecutive_stalls_before_shed: u8,
pub(crate) max_consecutive_stalls_before_close: u8,
pub(crate) soft_bucket_count: usize,
pub(crate) soft_bucket_share_pct: u8,
pub(crate) default_flow_weight: u8,
pub(crate) quickack_flow_weight: u8,
pub(crate) pressure: PressureConfig,
}
impl Default for WorkerFairnessConfig {
fn default() -> Self {
Self {
worker_id: 0,
backpressure_enabled: true,
max_active_flows: 4096,
max_total_queued_bytes: 16 * 1024 * 1024,
max_flow_queued_bytes: 512 * 1024,
base_quantum_bytes: 32 * 1024,
pressured_quantum_bytes: 16 * 1024,
penalized_quantum_bytes: 8 * 1024,
standing_queue_min_age: Duration::from_millis(250),
standing_queue_min_backlog_bytes: 64 * 1024,
standing_stall_threshold: 3,
max_consecutive_stalls_before_shed: 4,
max_consecutive_stalls_before_close: 16,
soft_bucket_count: 64,
soft_bucket_share_pct: 25,
default_flow_weight: 1,
quickack_flow_weight: 4,
pressure: PressureConfig::default(),
}
}
}
struct FlowEntry {
fairness: FlowFairnessState,
queue: VecDeque<QueuedFrame>,
}
impl FlowEntry {
fn new(flow_id: u64, worker_id: u16, bucket_id: usize, weight_quanta: u8) -> Self {
Self {
fairness: FlowFairnessState::new(flow_id, worker_id, bucket_id, weight_quanta),
queue: VecDeque::new(),
}
}
}
#[derive(Debug, Clone, Copy, Default)]
pub(crate) struct WorkerFairnessSnapshot {
pub(crate) pressure_state: PressureState,
pub(crate) active_flows: usize,
pub(crate) total_queued_bytes: u64,
pub(crate) standing_flows: usize,
pub(crate) backpressured_flows: usize,
pub(crate) scheduler_rounds: u64,
pub(crate) deficit_grants: u64,
pub(crate) deficit_skips: u64,
pub(crate) enqueue_rejects: u64,
pub(crate) shed_drops: u64,
pub(crate) fairness_penalties: u64,
pub(crate) downstream_stalls: u64,
}
pub(crate) struct WorkerFairnessState {
config: WorkerFairnessConfig,
pressure: PressureEvaluator,
flows: HashMap<u64, FlowEntry>,
active_ring: VecDeque<u64>,
active_ring_members: HashSet<u64>,
total_queued_bytes: u64,
bucket_queued_bytes: Vec<u64>,
bucket_active_flows: Vec<usize>,
standing_flow_count: usize,
backpressured_flow_count: usize,
scheduler_rounds: u64,
deficit_grants: u64,
deficit_skips: u64,
enqueue_rejects: u64,
shed_drops: u64,
fairness_penalties: u64,
downstream_stalls: u64,
}
impl WorkerFairnessState {
pub(crate) fn new(mut config: WorkerFairnessConfig, now: Instant) -> Self {
config.pressure.backpressure_enabled = config.backpressure_enabled;
let bucket_count = config.soft_bucket_count.max(1);
Self {
config,
pressure: PressureEvaluator::new(now),
flows: HashMap::new(),
active_ring: VecDeque::new(),
active_ring_members: HashSet::new(),
total_queued_bytes: 0,
bucket_queued_bytes: vec![0; bucket_count],
bucket_active_flows: vec![0; bucket_count],
standing_flow_count: 0,
backpressured_flow_count: 0,
scheduler_rounds: 0,
deficit_grants: 0,
deficit_skips: 0,
enqueue_rejects: 0,
shed_drops: 0,
fairness_penalties: 0,
downstream_stalls: 0,
}
}
pub(crate) fn pressure_state(&self) -> PressureState {
self.pressure.state()
}
pub(crate) fn set_backpressure_enabled(&mut self, enabled: bool) {
if self.config.backpressure_enabled == enabled {
return;
}
self.config.backpressure_enabled = enabled;
self.config.pressure.backpressure_enabled = enabled;
self.evaluate_pressure(Instant::now(), true);
}
pub(crate) fn snapshot(&self) -> WorkerFairnessSnapshot {
WorkerFairnessSnapshot {
pressure_state: self.pressure.state(),
active_flows: self.flows.len(),
total_queued_bytes: self.total_queued_bytes,
standing_flows: self.standing_flow_count,
backpressured_flows: self.backpressured_flow_count,
scheduler_rounds: self.scheduler_rounds,
deficit_grants: self.deficit_grants,
deficit_skips: self.deficit_skips,
enqueue_rejects: self.enqueue_rejects,
shed_drops: self.shed_drops,
fairness_penalties: self.fairness_penalties,
downstream_stalls: self.downstream_stalls,
}
}
pub(crate) fn enqueue_data(
&mut self,
conn_id: u64,
flags: u32,
data: Bytes,
now: Instant,
) -> AdmissionDecision {
let frame = QueuedFrame {
conn_id,
flags,
data,
enqueued_at: now,
};
let frame_bytes = frame.queued_bytes();
if self.config.backpressure_enabled && self.pressure.state() == PressureState::Saturated {
self.pressure
.note_admission_reject(now, &self.config.pressure);
self.enqueue_rejects = self.enqueue_rejects.saturating_add(1);
return AdmissionDecision::RejectSaturated;
}
if self.total_queued_bytes.saturating_add(frame_bytes) > self.config.max_total_queued_bytes
{
self.pressure
.note_admission_reject(now, &self.config.pressure);
self.enqueue_rejects = self.enqueue_rejects.saturating_add(1);
self.evaluate_pressure(now, true);
return AdmissionDecision::RejectWorkerCap;
}
if !self.flows.contains_key(&conn_id) && self.flows.len() >= self.config.max_active_flows {
self.pressure
.note_admission_reject(now, &self.config.pressure);
self.enqueue_rejects = self.enqueue_rejects.saturating_add(1);
self.evaluate_pressure(now, true);
return AdmissionDecision::RejectWorkerCap;
}
let bucket_id = self.bucket_for(conn_id);
let frame_weight = Self::weight_for_flags(&self.config, flags);
let bucket_cap = self
.config
.max_total_queued_bytes
.saturating_mul(self.config.soft_bucket_share_pct.max(1) as u64)
.saturating_div(100)
.max(self.config.max_flow_queued_bytes);
if self.bucket_queued_bytes[bucket_id].saturating_add(frame_bytes) > bucket_cap {
self.pressure
.note_admission_reject(now, &self.config.pressure);
self.enqueue_rejects = self.enqueue_rejects.saturating_add(1);
self.evaluate_pressure(now, true);
return AdmissionDecision::RejectBucketCap;
}
let entry = if let Some(flow) = self.flows.get_mut(&conn_id) {
flow
} else {
self.bucket_active_flows[bucket_id] =
self.bucket_active_flows[bucket_id].saturating_add(1);
self.flows.insert(
conn_id,
FlowEntry::new(conn_id, self.config.worker_id, bucket_id, frame_weight),
);
self.flows
.get_mut(&conn_id)
.expect("flow inserted must be retrievable")
};
entry.fairness.weight_quanta = entry.fairness.weight_quanta.max(frame_weight);
if entry.fairness.pending_bytes.saturating_add(frame_bytes)
> self.config.max_flow_queued_bytes
{
self.pressure
.note_admission_reject(now, &self.config.pressure);
self.enqueue_rejects = self.enqueue_rejects.saturating_add(1);
self.evaluate_pressure(now, true);
return AdmissionDecision::RejectFlowCap;
}
if self.config.backpressure_enabled
&& self.pressure.state() >= PressureState::Shedding
&& entry.fairness.standing_state == StandingQueueState::Standing
{
self.pressure
.note_admission_reject(now, &self.config.pressure);
self.enqueue_rejects = self.enqueue_rejects.saturating_add(1);
self.evaluate_pressure(now, true);
return AdmissionDecision::RejectStandingFlow;
}
entry.fairness.pending_bytes = entry.fairness.pending_bytes.saturating_add(frame_bytes);
if entry.fairness.queue_started_at.is_none() {
entry.fairness.queue_started_at = Some(now);
}
entry.queue.push_back(frame);
self.total_queued_bytes = self.total_queued_bytes.saturating_add(frame_bytes);
self.bucket_queued_bytes[bucket_id] =
self.bucket_queued_bytes[bucket_id].saturating_add(frame_bytes);
let mut enqueue_active = false;
if !entry.fairness.in_active_ring {
entry.fairness.in_active_ring = true;
enqueue_active = true;
}
let pressure_state = self.pressure.state();
let (before_membership, after_membership) = {
let before = Self::flow_membership(&entry.fairness);
Self::classify_flow(&self.config, pressure_state, now, &mut entry.fairness);
let after = Self::flow_membership(&entry.fairness);
(before, after)
};
if enqueue_active {
self.enqueue_active_conn(conn_id);
}
self.apply_flow_membership_delta(before_membership, after_membership);
self.evaluate_pressure(now, true);
AdmissionDecision::Admit
}
pub(crate) fn next_decision(&mut self, now: Instant) -> SchedulerDecision {
self.scheduler_rounds = self.scheduler_rounds.saturating_add(1);
self.evaluate_pressure(now, false);
let active_len = self.active_ring.len();
for _ in 0..active_len {
let Some(conn_id) = self.active_ring.pop_front() else {
break;
};
if !self.active_ring_members.remove(&conn_id) {
continue;
}
let mut candidate = None;
let mut requeue_active = false;
let mut drained_bytes = 0u64;
let mut bucket_id = 0usize;
let mut should_continue = false;
let mut enqueue_active = false;
let mut membership_delta = None;
let pressure_state = self.pressure.state();
if let Some(flow) = self.flows.get_mut(&conn_id) {
bucket_id = flow.fairness.bucket_id;
flow.fairness.in_active_ring = false;
let before_membership = Self::flow_membership(&flow.fairness);
if flow.queue.is_empty() {
flow.fairness.in_active_ring = false;
flow.fairness.scheduler_state = FlowSchedulerState::Idle;
flow.fairness.pending_bytes = 0;
flow.fairness.deficit_bytes = 0;
flow.fairness.queue_started_at = None;
should_continue = true;
} else {
Self::classify_flow(&self.config, pressure_state, now, &mut flow.fairness);
let quantum =
Self::effective_quantum_bytes(&self.config, pressure_state, &flow.fairness);
flow.fairness.deficit_bytes = flow
.fairness
.deficit_bytes
.saturating_add(i64::from(quantum));
Self::clamp_deficit_bytes(&self.config, &mut flow.fairness);
self.deficit_grants = self.deficit_grants.saturating_add(1);
let front_len = flow.queue.front().map_or(0, |front| front.queued_bytes());
if flow.fairness.deficit_bytes < front_len as i64 {
flow.fairness.consecutive_skips =
flow.fairness.consecutive_skips.saturating_add(1);
self.deficit_skips = self.deficit_skips.saturating_add(1);
requeue_active = true;
flow.fairness.in_active_ring = true;
enqueue_active = true;
} else if let Some(frame) = flow.queue.pop_front() {
drained_bytes = frame.queued_bytes();
flow.fairness.pending_bytes =
flow.fairness.pending_bytes.saturating_sub(drained_bytes);
flow.fairness.deficit_bytes = flow
.fairness
.deficit_bytes
.saturating_sub(drained_bytes as i64);
Self::clamp_deficit_bytes(&self.config, &mut flow.fairness);
flow.fairness.consecutive_skips = 0;
flow.fairness.queue_started_at =
flow.queue.front().map(|front| front.enqueued_at);
requeue_active = !flow.queue.is_empty();
if !requeue_active {
flow.fairness.scheduler_state = FlowSchedulerState::Idle;
flow.fairness.in_active_ring = false;
flow.fairness.deficit_bytes = 0;
} else {
flow.fairness.in_active_ring = true;
enqueue_active = true;
}
candidate = Some(DispatchCandidate {
pressure_state,
flow_class: flow.fairness.pressure_class,
frame,
});
}
}
membership_delta = Some((before_membership, Self::flow_membership(&flow.fairness)));
}
if let Some((before_membership, after_membership)) = membership_delta {
self.apply_flow_membership_delta(before_membership, after_membership);
}
if should_continue {
continue;
}
if drained_bytes > 0 {
self.total_queued_bytes = self.total_queued_bytes.saturating_sub(drained_bytes);
self.bucket_queued_bytes[bucket_id] =
self.bucket_queued_bytes[bucket_id].saturating_sub(drained_bytes);
}
if requeue_active && enqueue_active {
self.enqueue_active_conn(conn_id);
}
if let Some(candidate) = candidate {
return SchedulerDecision::Dispatch(candidate);
}
}
SchedulerDecision::Idle
}
pub(crate) fn apply_dispatch_feedback(
&mut self,
conn_id: u64,
candidate: DispatchCandidate,
feedback: DispatchFeedback,
now: Instant,
) -> DispatchAction {
match feedback {
DispatchFeedback::Routed => {
let mut membership_delta = None;
if let Some(flow) = self.flows.get_mut(&conn_id) {
let before_membership = Self::flow_membership(&flow.fairness);
flow.fairness.last_drain_at = Some(now);
flow.fairness.recent_drain_bytes = flow
.fairness
.recent_drain_bytes
.saturating_add(candidate.frame.queued_bytes());
flow.fairness.consecutive_stalls = 0;
if flow.fairness.scheduler_state != FlowSchedulerState::Idle {
flow.fairness.scheduler_state = FlowSchedulerState::Active;
}
Self::classify_flow(
&self.config,
self.pressure.state(),
now,
&mut flow.fairness,
);
membership_delta =
Some((before_membership, Self::flow_membership(&flow.fairness)));
}
if let Some((before_membership, after_membership)) = membership_delta {
self.apply_flow_membership_delta(before_membership, after_membership);
}
self.evaluate_pressure(now, false);
DispatchAction::Continue
}
DispatchFeedback::QueueFull => {
if self.config.backpressure_enabled {
self.pressure.note_route_stall(now, &self.config.pressure);
self.downstream_stalls = self.downstream_stalls.saturating_add(1);
}
let state = self.pressure.state();
let Some(flow) = self.flows.get_mut(&conn_id) else {
self.evaluate_pressure(now, true);
return DispatchAction::Continue;
};
let (before_membership, after_membership, should_close_flow, enqueue_active) = {
let before_membership = Self::flow_membership(&flow.fairness);
let mut enqueue_active = false;
if self.config.backpressure_enabled {
flow.fairness.consecutive_stalls =
flow.fairness.consecutive_stalls.saturating_add(1);
flow.fairness.scheduler_state = FlowSchedulerState::Backpressured;
flow.fairness.pressure_class = FlowPressureClass::Backpressured;
}
let should_shed_frame = self.config.backpressure_enabled
&& (matches!(state, PressureState::Saturated)
|| (matches!(state, PressureState::Shedding)
&& flow.fairness.standing_state == StandingQueueState::Standing
&& flow.fairness.consecutive_stalls
>= self.config.max_consecutive_stalls_before_shed));
if should_shed_frame {
self.shed_drops = self.shed_drops.saturating_add(1);
self.fairness_penalties = self.fairness_penalties.saturating_add(1);
} else {
let frame_bytes = candidate.frame.queued_bytes();
flow.queue.push_front(candidate.frame);
flow.fairness.pending_bytes =
flow.fairness.pending_bytes.saturating_add(frame_bytes);
flow.fairness.queue_started_at =
flow.queue.front().map(|front| front.enqueued_at);
self.total_queued_bytes =
self.total_queued_bytes.saturating_add(frame_bytes);
self.bucket_queued_bytes[flow.fairness.bucket_id] = self
.bucket_queued_bytes[flow.fairness.bucket_id]
.saturating_add(frame_bytes);
if !flow.fairness.in_active_ring {
flow.fairness.in_active_ring = true;
enqueue_active = true;
}
}
Self::classify_flow(&self.config, state, now, &mut flow.fairness);
let after_membership = Self::flow_membership(&flow.fairness);
let should_close_flow = self.config.backpressure_enabled
&& flow.fairness.consecutive_stalls
>= self.config.max_consecutive_stalls_before_close
&& self.pressure.state() == PressureState::Saturated;
(
before_membership,
after_membership,
should_close_flow,
enqueue_active,
)
};
if enqueue_active {
self.enqueue_active_conn(conn_id);
}
self.apply_flow_membership_delta(before_membership, after_membership);
if should_close_flow {
self.remove_flow(conn_id);
self.evaluate_pressure(now, true);
return DispatchAction::CloseFlow;
}
self.evaluate_pressure(now, true);
DispatchAction::Continue
}
DispatchFeedback::ChannelClosed | DispatchFeedback::NoConn => {
self.remove_flow(conn_id);
self.evaluate_pressure(now, true);
DispatchAction::CloseFlow
}
}
}
pub(crate) fn remove_flow(&mut self, conn_id: u64) {
let Some(entry) = self.flows.remove(&conn_id) else {
return;
};
self.active_ring_members.remove(&conn_id);
self.active_ring
.retain(|queued_conn_id| *queued_conn_id != conn_id);
let (was_standing, was_backpressured) = Self::flow_membership(&entry.fairness);
if was_standing {
self.standing_flow_count = self.standing_flow_count.saturating_sub(1);
}
if was_backpressured {
self.backpressured_flow_count = self.backpressured_flow_count.saturating_sub(1);
}
self.bucket_active_flows[entry.fairness.bucket_id] =
self.bucket_active_flows[entry.fairness.bucket_id].saturating_sub(1);
let mut reclaimed = 0u64;
for frame in entry.queue {
reclaimed = reclaimed.saturating_add(frame.queued_bytes());
}
self.total_queued_bytes = self.total_queued_bytes.saturating_sub(reclaimed);
self.bucket_queued_bytes[entry.fairness.bucket_id] =
self.bucket_queued_bytes[entry.fairness.bucket_id].saturating_sub(reclaimed);
}
fn evaluate_pressure(&mut self, now: Instant, force: bool) {
let _ = self.pressure.maybe_evaluate(
now,
&self.config.pressure,
self.config.max_total_queued_bytes,
PressureSignals {
active_flows: self.flows.len(),
total_queued_bytes: self.total_queued_bytes,
standing_flows: self.standing_flow_count,
backpressured_flows: self.backpressured_flow_count,
},
force,
);
}
fn classify_flow(
config: &WorkerFairnessConfig,
pressure_state: PressureState,
now: Instant,
fairness: &mut FlowFairnessState,
) {
let (pressure_class, standing_state, scheduler_state, standing) =
Self::derive_flow_classification(config, pressure_state, now, fairness);
fairness.pressure_class = pressure_class;
fairness.standing_state = standing_state;
fairness.scheduler_state = scheduler_state;
if scheduler_state == FlowSchedulerState::Idle {
fairness.deficit_bytes = 0;
}
if standing {
fairness.penalty_score = fairness.penalty_score.saturating_add(1);
} else {
fairness.penalty_score = fairness.penalty_score.saturating_sub(1);
}
}
fn derive_flow_classification(
config: &WorkerFairnessConfig,
pressure_state: PressureState,
now: Instant,
fairness: &FlowFairnessState,
) -> (
FlowPressureClass,
StandingQueueState,
FlowSchedulerState,
bool,
) {
if fairness.pending_bytes == 0 {
return (
FlowPressureClass::Healthy,
StandingQueueState::Transient,
FlowSchedulerState::Idle,
false,
);
}
let queue_age = fairness
.queue_started_at
.map(|ts| now.saturating_duration_since(ts))
.unwrap_or_default();
let drain_stalled = fairness
.last_drain_at
.map(|ts| now.saturating_duration_since(ts) >= config.standing_queue_min_age)
.unwrap_or(true);
let standing = fairness.pending_bytes >= config.standing_queue_min_backlog_bytes
&& queue_age >= config.standing_queue_min_age
&& (fairness.consecutive_stalls >= config.standing_stall_threshold || drain_stalled);
if standing {
let scheduler_state = if pressure_state >= PressureState::Shedding {
FlowSchedulerState::SheddingCandidate
} else {
FlowSchedulerState::Penalized
};
return (
FlowPressureClass::Standing,
StandingQueueState::Standing,
scheduler_state,
true,
);
}
if fairness.consecutive_stalls > 0 {
return (
FlowPressureClass::Backpressured,
StandingQueueState::Transient,
FlowSchedulerState::Backpressured,
false,
);
}
if fairness.pending_bytes >= config.standing_queue_min_backlog_bytes {
return (
FlowPressureClass::Bursty,
StandingQueueState::Transient,
FlowSchedulerState::Active,
false,
);
}
(
FlowPressureClass::Healthy,
StandingQueueState::Transient,
FlowSchedulerState::Active,
false,
)
}
#[inline]
fn flow_membership(fairness: &FlowFairnessState) -> (bool, bool) {
(
fairness.standing_state == StandingQueueState::Standing,
Self::scheduler_state_is_backpressured(fairness.scheduler_state),
)
}
#[inline]
fn scheduler_state_is_backpressured(state: FlowSchedulerState) -> bool {
matches!(
state,
FlowSchedulerState::Backpressured
| FlowSchedulerState::Penalized
| FlowSchedulerState::SheddingCandidate
)
}
fn apply_flow_membership_delta(
&mut self,
before_membership: (bool, bool),
after_membership: (bool, bool),
) {
if before_membership.0 != after_membership.0 {
if after_membership.0 {
self.standing_flow_count = self.standing_flow_count.saturating_add(1);
} else {
self.standing_flow_count = self.standing_flow_count.saturating_sub(1);
}
}
if before_membership.1 != after_membership.1 {
if after_membership.1 {
self.backpressured_flow_count = self.backpressured_flow_count.saturating_add(1);
} else {
self.backpressured_flow_count = self.backpressured_flow_count.saturating_sub(1);
}
}
}
#[inline]
fn clamp_deficit_bytes(config: &WorkerFairnessConfig, fairness: &mut FlowFairnessState) {
let max_deficit = config.max_flow_queued_bytes.min(i64::MAX as u64) as i64;
fairness.deficit_bytes = fairness.deficit_bytes.clamp(0, max_deficit);
}
#[inline]
fn enqueue_active_conn(&mut self, conn_id: u64) {
if self.active_ring_members.insert(conn_id) {
self.active_ring.push_back(conn_id);
}
}
#[inline]
fn weight_for_flags(config: &WorkerFairnessConfig, flags: u32) -> u8 {
if (flags & RPC_FLAG_QUICKACK) != 0 {
return config.quickack_flow_weight.max(1);
}
config.default_flow_weight.max(1)
}
#[cfg(test)]
pub(crate) fn debug_recompute_flow_counters(&self, now: Instant) -> (usize, usize) {
let pressure_state = self.pressure.state();
let mut standing = 0usize;
let mut backpressured = 0usize;
for flow in self.flows.values() {
let (_, standing_state, scheduler_state, _) =
Self::derive_flow_classification(&self.config, pressure_state, now, &flow.fairness);
if standing_state == StandingQueueState::Standing {
standing = standing.saturating_add(1);
}
if Self::scheduler_state_is_backpressured(scheduler_state) {
backpressured = backpressured.saturating_add(1);
}
}
(standing, backpressured)
}
#[cfg(test)]
pub(crate) fn debug_check_active_ring_consistency(&self) -> bool {
if self.active_ring.len() != self.active_ring_members.len() {
return false;
}
let mut seen = HashSet::with_capacity(self.active_ring.len());
for conn_id in self.active_ring.iter().copied() {
if !seen.insert(conn_id) {
return false;
}
if !self.active_ring_members.contains(&conn_id) {
return false;
}
let Some(flow) = self.flows.get(&conn_id) else {
return false;
};
if !flow.fairness.in_active_ring || flow.queue.is_empty() {
return false;
}
}
for (conn_id, flow) in self.flows.iter() {
let in_ring = self.active_ring_members.contains(conn_id);
if flow.fairness.in_active_ring != in_ring {
return false;
}
if in_ring && flow.queue.is_empty() {
return false;
}
}
true
}
#[cfg(test)]
pub(crate) fn debug_max_deficit_bytes(&self) -> i64 {
self.flows
.values()
.map(|entry| entry.fairness.deficit_bytes)
.max()
.unwrap_or(0)
}
fn effective_quantum_bytes(
config: &WorkerFairnessConfig,
pressure_state: PressureState,
fairness: &FlowFairnessState,
) -> u32 {
let penalized = matches!(
fairness.scheduler_state,
FlowSchedulerState::Penalized | FlowSchedulerState::SheddingCandidate
);
if penalized {
return config.penalized_quantum_bytes.max(1);
}
let base_quantum = match pressure_state {
PressureState::Normal => config.base_quantum_bytes.max(1),
PressureState::Pressured => config.pressured_quantum_bytes.max(1),
PressureState::Shedding => config.pressured_quantum_bytes.max(1),
PressureState::Saturated => config.penalized_quantum_bytes.max(1),
};
let weighted_quantum = base_quantum.saturating_mul(fairness.weight_quanta.max(1) as u32);
weighted_quantum.max(1)
}
fn bucket_for(&self, conn_id: u64) -> usize {
(conn_id as usize) % self.bucket_queued_bytes.len().max(1)
}
}

View File

@@ -1794,6 +1794,8 @@ mod tests {
MeSocksKdfPolicy::default(),
general.me_writer_cmd_channel_capacity,
general.me_route_channel_capacity,
general.me_route_backpressure_enabled,
general.me_route_fairshare_enabled,
general.me_route_backpressure_base_timeout_ms,
general.me_route_backpressure_high_timeout_ms,
general.me_route_backpressure_high_watermark_pct,

View File

@@ -2,6 +2,10 @@
mod codec;
mod config_updater;
mod fairness;
#[cfg(test)]
#[path = "tests/fairness_security_tests.rs"]
mod fairness_security_tests;
mod handshake;
mod health;
#[cfg(test)]

View File

@@ -396,6 +396,8 @@ pub(super) struct WriterSelectionPolicyCore {
pub(super) struct TransportPolicyCore {
pub(super) me_socks_kdf_policy: AtomicU8,
pub(super) me_route_backpressure_enabled: Arc<AtomicBool>,
pub(super) me_route_fairshare_enabled: Arc<AtomicBool>,
pub(super) me_reader_route_data_wait_ms: Arc<AtomicU64>,
}
@@ -548,6 +550,8 @@ impl MePool {
me_socks_kdf_policy: MeSocksKdfPolicy,
me_writer_cmd_channel_capacity: usize,
me_route_channel_capacity: usize,
me_route_backpressure_enabled: bool,
me_route_fairshare_enabled: bool,
me_route_backpressure_base_timeout_ms: u64,
me_route_backpressure_high_timeout_ms: u64,
me_route_backpressure_high_watermark_pct: u8,
@@ -783,6 +787,10 @@ impl MePool {
}),
transport_policy: Arc::new(TransportPolicyCore {
me_socks_kdf_policy: AtomicU8::new(me_socks_kdf_policy.as_u8()),
me_route_backpressure_enabled: Arc::new(AtomicBool::new(
me_route_backpressure_enabled,
)),
me_route_fairshare_enabled: Arc::new(AtomicBool::new(me_route_fairshare_enabled)),
me_reader_route_data_wait_ms: Arc::new(AtomicU64::new(
me_reader_route_data_wait_ms,
)),
@@ -1245,6 +1253,8 @@ impl MePool {
pub fn update_runtime_transport_policy(
&self,
socks_kdf_policy: MeSocksKdfPolicy,
route_backpressure_enabled: bool,
route_fairshare_enabled: bool,
route_backpressure_base_timeout_ms: u64,
route_backpressure_high_timeout_ms: u64,
route_backpressure_high_watermark_pct: u8,
@@ -1253,6 +1263,12 @@ impl MePool {
self.transport_policy
.me_socks_kdf_policy
.store(socks_kdf_policy.as_u8(), Ordering::Relaxed);
self.transport_policy
.me_route_backpressure_enabled
.store(route_backpressure_enabled, Ordering::Relaxed);
self.transport_policy
.me_route_fairshare_enabled
.store(route_fairshare_enabled, Ordering::Relaxed);
self.transport_policy
.me_reader_route_data_wait_ms
.store(reader_route_data_wait_ms, Ordering::Relaxed);

View File

@@ -436,6 +436,9 @@ impl MePool {
let cancel_signal = cancel.clone();
let cancel_select = cancel.clone();
let cancel_cleanup = cancel.clone();
let route_backpressure_enabled =
self.transport_policy.me_route_backpressure_enabled.clone();
let route_fairshare_enabled = self.transport_policy.me_route_fairshare_enabled.clone();
let reader_route_data_wait_ms = self.transport_policy.me_reader_route_data_wait_ms.clone();
tokio::spawn(async move {
@@ -458,6 +461,8 @@ impl MePool {
writer_id,
degraded,
rtt_ema_ms_x10,
route_backpressure_enabled,
route_fairshare_enabled,
reader_route_data_wait_ms,
cancel_reader,
) => WriterLifecycleExit::Reader(reader_res),

View File

@@ -4,7 +4,7 @@ use std::collections::HashMap;
use std::io::ErrorKind;
use std::sync::Arc;
use std::sync::atomic::{AtomicBool, AtomicU32, AtomicU64, Ordering};
use std::time::Instant;
use std::time::{Duration, Instant};
use bytes::{Bytes, BytesMut};
use tokio::io::AsyncReadExt;
@@ -20,11 +20,15 @@ use crate::protocol::constants::*;
use crate::stats::Stats;
use super::codec::{RpcChecksumMode, WriterCommand, rpc_crc};
use super::fairness::{
AdmissionDecision, DispatchAction, DispatchFeedback, PressureState, SchedulerDecision,
WorkerFairnessConfig, WorkerFairnessSnapshot, WorkerFairnessState,
};
use super::registry::RouteResult;
use super::{ConnRegistry, MeResponse};
const DATA_ROUTE_MAX_ATTEMPTS: usize = 3;
const DATA_ROUTE_QUEUE_FULL_STARVATION_THRESHOLD: u8 = 3;
const FAIRNESS_DRAIN_BUDGET_PER_LOOP: usize = 128;
fn should_close_on_route_result_for_data(result: RouteResult) -> bool {
matches!(result, RouteResult::NoConn | RouteResult::ChannelClosed)
@@ -41,10 +45,30 @@ fn is_data_route_queue_full(result: RouteResult) -> bool {
)
}
fn should_close_on_queue_full_streak(streak: u8) -> bool {
fn should_close_on_queue_full_streak_with_policy(
streak: u8,
pressure_state: PressureState,
backpressure_enabled: bool,
) -> bool {
if !backpressure_enabled {
return false;
}
if pressure_state < PressureState::Shedding {
return false;
}
streak >= DATA_ROUTE_QUEUE_FULL_STARVATION_THRESHOLD
}
fn should_schedule_fairness_retry(snapshot: &WorkerFairnessSnapshot) -> bool {
snapshot.total_queued_bytes > 0
}
fn fairness_retry_delay(route_wait_ms: u64) -> Duration {
Duration::from_millis(route_wait_ms.max(1))
}
async fn route_data_with_retry(
reg: &ConnRegistry,
conn_id: u64,
@@ -77,6 +101,123 @@ async fn route_data_with_retry(
}
}
#[inline]
fn route_feedback(result: RouteResult) -> DispatchFeedback {
match result {
RouteResult::Routed => DispatchFeedback::Routed,
RouteResult::NoConn => DispatchFeedback::NoConn,
RouteResult::ChannelClosed => DispatchFeedback::ChannelClosed,
RouteResult::QueueFullBase | RouteResult::QueueFullHigh => DispatchFeedback::QueueFull,
}
}
fn report_route_drop(result: RouteResult, stats: &Stats) {
match result {
RouteResult::NoConn => stats.increment_me_route_drop_no_conn(),
RouteResult::ChannelClosed => stats.increment_me_route_drop_channel_closed(),
RouteResult::QueueFullBase => {
stats.increment_me_route_drop_queue_full();
stats.increment_me_route_drop_queue_full_base();
}
RouteResult::QueueFullHigh => {
stats.increment_me_route_drop_queue_full();
stats.increment_me_route_drop_queue_full_high();
}
RouteResult::Routed => {}
}
}
fn apply_fairness_metrics_delta(
stats: &Stats,
prev: &mut WorkerFairnessSnapshot,
current: WorkerFairnessSnapshot,
) {
stats.set_me_fair_active_flows_gauge(current.active_flows as u64);
stats.set_me_fair_queued_bytes_gauge(current.total_queued_bytes);
stats.set_me_fair_standing_flows_gauge(current.standing_flows as u64);
stats.set_me_fair_backpressured_flows_gauge(current.backpressured_flows as u64);
stats.set_me_fair_pressure_state_gauge(current.pressure_state.as_u8() as u64);
stats.add_me_fair_scheduler_rounds_total(
current
.scheduler_rounds
.saturating_sub(prev.scheduler_rounds),
);
stats.add_me_fair_deficit_grants_total(
current.deficit_grants.saturating_sub(prev.deficit_grants),
);
stats.add_me_fair_deficit_skips_total(current.deficit_skips.saturating_sub(prev.deficit_skips));
stats.add_me_fair_enqueue_rejects_total(
current.enqueue_rejects.saturating_sub(prev.enqueue_rejects),
);
stats.add_me_fair_shed_drops_total(current.shed_drops.saturating_sub(prev.shed_drops));
stats.add_me_fair_penalties_total(
current
.fairness_penalties
.saturating_sub(prev.fairness_penalties),
);
stats.add_me_fair_downstream_stalls_total(
current
.downstream_stalls
.saturating_sub(prev.downstream_stalls),
);
*prev = current;
}
async fn drain_fairness_scheduler(
fairness: &mut WorkerFairnessState,
reg: &ConnRegistry,
tx: &mpsc::Sender<WriterCommand>,
data_route_queue_full_streak: &mut HashMap<u64, u8>,
backpressure_enabled: bool,
route_wait_ms: u64,
stats: &Stats,
) {
for _ in 0..FAIRNESS_DRAIN_BUDGET_PER_LOOP {
let now = Instant::now();
let SchedulerDecision::Dispatch(candidate) = fairness.next_decision(now) else {
break;
};
let cid = candidate.frame.conn_id;
let pressure_state = candidate.pressure_state;
let _flow_class = candidate.flow_class;
let routed = route_data_with_retry(
reg,
cid,
candidate.frame.flags,
candidate.frame.data.clone(),
route_wait_ms,
)
.await;
if matches!(routed, RouteResult::Routed) {
data_route_queue_full_streak.remove(&cid);
} else {
report_route_drop(routed, stats);
}
let action = fairness.apply_dispatch_feedback(cid, candidate, route_feedback(routed), now);
if is_data_route_queue_full(routed) {
let streak = data_route_queue_full_streak.entry(cid).or_insert(0);
*streak = streak.saturating_add(1);
if should_close_on_queue_full_streak_with_policy(
*streak,
pressure_state,
backpressure_enabled,
) {
fairness.remove_flow(cid);
data_route_queue_full_streak.remove(&cid);
reg.unregister(cid).await;
send_close_conn(tx, cid).await;
continue;
}
}
if action == DispatchAction::CloseFlow || should_close_on_route_result_for_data(routed) {
fairness.remove_flow(cid);
data_route_queue_full_streak.remove(&cid);
reg.unregister(cid).await;
send_close_conn(tx, cid).await;
}
}
}
pub(crate) async fn reader_loop(
mut rd: tokio::io::ReadHalf<TcpStream>,
dk: [u8; 32],
@@ -92,19 +233,64 @@ pub(crate) async fn reader_loop(
writer_id: u64,
degraded: Arc<AtomicBool>,
writer_rtt_ema_ms_x10: Arc<AtomicU32>,
route_backpressure_enabled: Arc<AtomicBool>,
route_fairshare_enabled: Arc<AtomicBool>,
reader_route_data_wait_ms: Arc<AtomicU64>,
cancel: CancellationToken,
) -> Result<()> {
let mut raw = enc_leftover;
let mut expected_seq: i32 = 0;
let mut data_route_queue_full_streak = HashMap::<u64, u8>::new();
let mut fairness = WorkerFairnessState::new(
WorkerFairnessConfig {
worker_id: (writer_id as u16).saturating_add(1),
max_active_flows: reg.route_channel_capacity().saturating_mul(4).max(256),
max_total_queued_bytes: (reg.route_channel_capacity() as u64)
.saturating_mul(16 * 1024)
.max(4 * 1024 * 1024),
max_flow_queued_bytes: (reg.route_channel_capacity() as u64)
.saturating_mul(2 * 1024)
.clamp(64 * 1024, 2 * 1024 * 1024),
backpressure_enabled: route_backpressure_enabled.load(Ordering::Relaxed),
..WorkerFairnessConfig::default()
},
Instant::now(),
);
let mut fairness_snapshot = fairness.snapshot();
loop {
let backpressure_enabled = route_backpressure_enabled.load(Ordering::Relaxed);
let fairshare_enabled = route_fairshare_enabled.load(Ordering::Relaxed);
fairness.set_backpressure_enabled(backpressure_enabled);
let fairness_has_backlog = should_schedule_fairness_retry(&fairness_snapshot);
let mut tmp = [0u8; 65_536];
let backlog_retry_enabled = fairness_has_backlog;
let backlog_retry_delay =
fairness_retry_delay(reader_route_data_wait_ms.load(Ordering::Relaxed));
let mut retry_only = false;
let n = tokio::select! {
res = rd.read(&mut tmp) => res.map_err(ProxyError::Io)?,
_ = tokio::time::sleep(backlog_retry_delay), if backlog_retry_enabled => {
retry_only = true;
0usize
},
_ = cancel.cancelled() => return Ok(()),
};
if retry_only {
let route_wait_ms = reader_route_data_wait_ms.load(Ordering::Relaxed);
drain_fairness_scheduler(
&mut fairness,
reg.as_ref(),
&tx,
&mut data_route_queue_full_streak,
backpressure_enabled,
route_wait_ms,
stats.as_ref(),
)
.await;
let current_snapshot = fairness.snapshot();
apply_fairness_metrics_delta(stats.as_ref(), &mut fairness_snapshot, current_snapshot);
continue;
}
if n == 0 {
stats.increment_me_reader_eof_total();
return Err(ProxyError::Io(std::io::Error::new(
@@ -181,39 +367,56 @@ pub(crate) async fn reader_loop(
let data = body.slice(12..);
trace!(cid, flags, len = data.len(), "RPC_PROXY_ANS");
let route_wait_ms = reader_route_data_wait_ms.load(Ordering::Relaxed);
let routed =
route_data_with_retry(reg.as_ref(), cid, flags, data, route_wait_ms).await;
if matches!(routed, RouteResult::Routed) {
data_route_queue_full_streak.remove(&cid);
continue;
}
match routed {
RouteResult::NoConn => stats.increment_me_route_drop_no_conn(),
RouteResult::ChannelClosed => stats.increment_me_route_drop_channel_closed(),
RouteResult::QueueFullBase => {
stats.increment_me_route_drop_queue_full();
stats.increment_me_route_drop_queue_full_base();
}
RouteResult::QueueFullHigh => {
if fairshare_enabled {
let admission = fairness.enqueue_data(cid, flags, data, Instant::now());
if !matches!(admission, AdmissionDecision::Admit) {
stats.increment_me_route_drop_queue_full();
stats.increment_me_route_drop_queue_full_high();
let streak = data_route_queue_full_streak.entry(cid).or_insert(0);
*streak = streak.saturating_add(1);
let pressure_state = fairness.pressure_state();
if should_close_on_queue_full_streak_with_policy(
*streak,
pressure_state,
backpressure_enabled,
) || (backpressure_enabled
&& matches!(admission, AdmissionDecision::RejectSaturated))
{
fairness.remove_flow(cid);
data_route_queue_full_streak.remove(&cid);
reg.unregister(cid).await;
send_close_conn(&tx, cid).await;
}
}
RouteResult::Routed => {}
}
if should_close_on_route_result_for_data(routed) {
data_route_queue_full_streak.remove(&cid);
reg.unregister(cid).await;
send_close_conn(&tx, cid).await;
continue;
}
if is_data_route_queue_full(routed) {
let streak = data_route_queue_full_streak.entry(cid).or_insert(0);
*streak = streak.saturating_add(1);
if should_close_on_queue_full_streak(*streak) {
} else {
let route_wait_ms = reader_route_data_wait_ms.load(Ordering::Relaxed);
let routed =
route_data_with_retry(reg.as_ref(), cid, flags, data, route_wait_ms).await;
if matches!(routed, RouteResult::Routed) {
data_route_queue_full_streak.remove(&cid);
continue;
}
report_route_drop(routed, stats.as_ref());
if should_close_on_route_result_for_data(routed) {
fairness.remove_flow(cid);
data_route_queue_full_streak.remove(&cid);
reg.unregister(cid).await;
send_close_conn(&tx, cid).await;
continue;
}
if is_data_route_queue_full(routed) {
let streak = data_route_queue_full_streak.entry(cid).or_insert(0);
*streak = streak.saturating_add(1);
if should_close_on_queue_full_streak_with_policy(
*streak,
PressureState::Shedding,
backpressure_enabled,
) {
fairness.remove_flow(cid);
data_route_queue_full_streak.remove(&cid);
reg.unregister(cid).await;
send_close_conn(&tx, cid).await;
}
}
}
} else if pt == RPC_SIMPLE_ACK_U32 && body.len() >= 12 {
@@ -249,12 +452,14 @@ pub(crate) async fn reader_loop(
let _ = reg.route_nowait(cid, MeResponse::Close).await;
reg.unregister(cid).await;
data_route_queue_full_streak.remove(&cid);
fairness.remove_flow(cid);
} else if pt == RPC_CLOSE_CONN_U32 && body.len() >= 8 {
let cid = u64::from_le_bytes(body[0..8].try_into().unwrap());
debug!(cid, "RPC_CLOSE_CONN from ME");
let _ = reg.route_nowait(cid, MeResponse::Close).await;
reg.unregister(cid).await;
data_route_queue_full_streak.remove(&cid);
fairness.remove_flow(cid);
} else if pt == RPC_PING_U32 && body.len() >= 8 {
let ping_id = i64::from_le_bytes(body[0..8].try_into().unwrap());
trace!(ping_id, "RPC_PING -> RPC_PONG");
@@ -310,20 +515,38 @@ pub(crate) async fn reader_loop(
"Unknown RPC"
);
}
let route_wait_ms = reader_route_data_wait_ms.load(Ordering::Relaxed);
drain_fairness_scheduler(
&mut fairness,
reg.as_ref(),
&tx,
&mut data_route_queue_full_streak,
backpressure_enabled,
route_wait_ms,
stats.as_ref(),
)
.await;
let current_snapshot = fairness.snapshot();
apply_fairness_metrics_delta(stats.as_ref(), &mut fairness_snapshot, current_snapshot);
}
}
}
#[cfg(test)]
mod tests {
use std::time::Duration;
use bytes::Bytes;
use super::PressureState;
use crate::transport::middle_proxy::ConnRegistry;
use super::{
MeResponse, RouteResult, is_data_route_queue_full, route_data_with_retry,
should_close_on_queue_full_streak, should_close_on_route_result_for_ack,
should_close_on_route_result_for_data,
MeResponse, RouteResult, WorkerFairnessSnapshot, fairness_retry_delay,
is_data_route_queue_full, route_data_with_retry,
should_close_on_queue_full_streak_with_policy, should_close_on_route_result_for_ack,
should_close_on_route_result_for_data, should_schedule_fairness_retry,
};
#[test]
@@ -346,10 +569,51 @@ mod tests {
assert!(is_data_route_queue_full(RouteResult::QueueFullBase));
assert!(is_data_route_queue_full(RouteResult::QueueFullHigh));
assert!(!is_data_route_queue_full(RouteResult::NoConn));
assert!(!should_close_on_queue_full_streak(1));
assert!(!should_close_on_queue_full_streak(2));
assert!(should_close_on_queue_full_streak(3));
assert!(should_close_on_queue_full_streak(u8::MAX));
assert!(!should_close_on_queue_full_streak_with_policy(
1,
PressureState::Normal,
true
));
assert!(!should_close_on_queue_full_streak_with_policy(
2,
PressureState::Pressured,
true
));
assert!(!should_close_on_queue_full_streak_with_policy(
3,
PressureState::Pressured,
true
));
assert!(should_close_on_queue_full_streak_with_policy(
3,
PressureState::Shedding,
true
));
assert!(should_close_on_queue_full_streak_with_policy(
u8::MAX,
PressureState::Saturated,
true
));
assert!(!should_close_on_queue_full_streak_with_policy(
u8::MAX,
PressureState::Saturated,
false
));
}
#[test]
fn fairness_retry_is_scheduled_only_when_queue_has_pending_bytes() {
let mut snapshot = WorkerFairnessSnapshot::default();
assert!(!should_schedule_fairness_retry(&snapshot));
snapshot.total_queued_bytes = 1;
assert!(should_schedule_fairness_retry(&snapshot));
}
#[test]
fn fairness_retry_delay_never_drops_below_one_millisecond() {
assert_eq!(fairness_retry_delay(0), Duration::from_millis(1));
assert_eq!(fairness_retry_delay(2), Duration::from_millis(2));
}
#[test]

View File

@@ -140,6 +140,10 @@ impl ConnRegistry {
}
}
pub fn route_channel_capacity(&self) -> usize {
self.route_channel_capacity
}
#[cfg(test)]
pub fn new() -> Self {
Self::with_route_channel_capacity(4096)

View File

@@ -37,20 +37,26 @@ pub(super) fn validate_proxy_secret_len(data_len: usize, max_len: usize) -> Resu
/// Fetch Telegram proxy-secret binary.
#[allow(dead_code)]
pub async fn fetch_proxy_secret(cache_path: Option<&str>, max_len: usize) -> Result<Vec<u8>> {
fetch_proxy_secret_with_upstream(cache_path, max_len, None).await
pub async fn fetch_proxy_secret(
cache_path: Option<&str>,
max_len: usize,
proxy_secret_url: Option<&str>,
) -> Result<Vec<u8>> {
fetch_proxy_secret_with_upstream(cache_path, max_len, proxy_secret_url, None).await
}
/// Fetch Telegram proxy-secret binary, optionally through upstream routing.
pub async fn fetch_proxy_secret_with_upstream(
cache_path: Option<&str>,
max_len: usize,
proxy_secret_url: Option<&str>,
upstream: Option<Arc<UpstreamManager>>,
) -> Result<Vec<u8>> {
let cache = cache_path.unwrap_or("proxy-secret");
// 1) Try fresh download first.
match download_proxy_secret_with_max_len_via_upstream(max_len, upstream).await {
match download_proxy_secret_with_max_len_via_upstream(max_len, upstream, proxy_secret_url).await
{
Ok(data) => {
if let Err(e) = tokio::fs::write(cache, &data).await {
warn!(error = %e, "Failed to cache proxy-secret (non-fatal)");
@@ -91,14 +97,19 @@ pub async fn fetch_proxy_secret_with_upstream(
#[allow(dead_code)]
pub async fn download_proxy_secret_with_max_len(max_len: usize) -> Result<Vec<u8>> {
download_proxy_secret_with_max_len_via_upstream(max_len, None).await
download_proxy_secret_with_max_len_via_upstream(max_len, None, None).await
}
pub async fn download_proxy_secret_with_max_len_via_upstream(
max_len: usize,
upstream: Option<Arc<UpstreamManager>>,
proxy_secret_url: Option<&str>,
) -> Result<Vec<u8>> {
let resp = https_get("https://core.telegram.org/getProxySecret", upstream).await?;
let resp = https_get(
proxy_secret_url.unwrap_or("https://core.telegram.org/getProxySecret"),
upstream,
)
.await?;
if !(200..=299).contains(&resp.status) {
return Err(ProxyError::Proxy(format!(

View File

@@ -0,0 +1,248 @@
use std::time::{Duration, Instant};
use bytes::Bytes;
use crate::protocol::constants::RPC_FLAG_QUICKACK;
use crate::transport::middle_proxy::fairness::{
AdmissionDecision, DispatchAction, DispatchFeedback, PressureState, SchedulerDecision,
WorkerFairnessConfig, WorkerFairnessState,
};
fn enqueue_payload(size: usize) -> Bytes {
Bytes::from(vec![0xAB; size])
}
#[test]
fn fairness_rejects_when_worker_budget_is_exhausted() {
let now = Instant::now();
let mut fairness = WorkerFairnessState::new(
WorkerFairnessConfig {
max_total_queued_bytes: 1024,
max_flow_queued_bytes: 1024,
..WorkerFairnessConfig::default()
},
now,
);
assert_eq!(
fairness.enqueue_data(1, 0, enqueue_payload(700), now),
AdmissionDecision::Admit
);
assert_eq!(
fairness.enqueue_data(2, 0, enqueue_payload(400), now),
AdmissionDecision::RejectWorkerCap
);
let snapshot = fairness.snapshot();
assert!(snapshot.total_queued_bytes <= 1024);
assert_eq!(snapshot.enqueue_rejects, 1);
}
#[test]
fn fairness_marks_standing_queue_after_stall_and_age_threshold() {
let mut now = Instant::now();
let mut fairness = WorkerFairnessState::new(
WorkerFairnessConfig {
standing_queue_min_age: Duration::from_millis(50),
standing_queue_min_backlog_bytes: 256,
standing_stall_threshold: 1,
max_flow_queued_bytes: 4096,
max_total_queued_bytes: 4096,
..WorkerFairnessConfig::default()
},
now,
);
assert_eq!(
fairness.enqueue_data(11, 0, enqueue_payload(512), now),
AdmissionDecision::Admit
);
now += Duration::from_millis(100);
let SchedulerDecision::Dispatch(candidate) = fairness.next_decision(now) else {
panic!("expected dispatch candidate");
};
let action = fairness.apply_dispatch_feedback(11, candidate, DispatchFeedback::QueueFull, now);
assert!(matches!(action, DispatchAction::Continue));
let snapshot = fairness.snapshot();
assert_eq!(snapshot.standing_flows, 1);
assert!(snapshot.backpressured_flows >= 1);
}
#[test]
fn fairness_keeps_fast_flow_progress_under_slow_neighbor() {
let mut now = Instant::now();
let mut fairness = WorkerFairnessState::new(
WorkerFairnessConfig {
max_total_queued_bytes: 64 * 1024,
max_flow_queued_bytes: 32 * 1024,
..WorkerFairnessConfig::default()
},
now,
);
for _ in 0..16 {
assert_eq!(
fairness.enqueue_data(1, 0, enqueue_payload(512), now),
AdmissionDecision::Admit
);
assert_eq!(
fairness.enqueue_data(2, 0, enqueue_payload(512), now),
AdmissionDecision::Admit
);
}
let mut fast_routed = 0u64;
for _ in 0..128 {
now += Duration::from_millis(5);
let SchedulerDecision::Dispatch(candidate) = fairness.next_decision(now) else {
break;
};
let cid = candidate.frame.conn_id;
let feedback = if cid == 2 {
DispatchFeedback::QueueFull
} else {
fast_routed = fast_routed.saturating_add(1);
DispatchFeedback::Routed
};
let _ = fairness.apply_dispatch_feedback(cid, candidate, feedback, now);
}
let snapshot = fairness.snapshot();
assert!(fast_routed > 0, "fast flow must continue making progress");
assert!(snapshot.total_queued_bytes <= 64 * 1024);
}
#[test]
fn fairness_prioritizes_quickack_flow_when_weights_enabled() {
let mut now = Instant::now();
let mut fairness = WorkerFairnessState::new(
WorkerFairnessConfig {
max_total_queued_bytes: 256 * 1024,
max_flow_queued_bytes: 128 * 1024,
base_quantum_bytes: 8 * 1024,
pressured_quantum_bytes: 8 * 1024,
penalized_quantum_bytes: 8 * 1024,
default_flow_weight: 1,
quickack_flow_weight: 4,
..WorkerFairnessConfig::default()
},
now,
);
for _ in 0..8 {
assert_eq!(
fairness.enqueue_data(10, RPC_FLAG_QUICKACK, enqueue_payload(16 * 1024), now),
AdmissionDecision::Admit
);
assert_eq!(
fairness.enqueue_data(20, 0, enqueue_payload(16 * 1024), now),
AdmissionDecision::Admit
);
}
let mut quickack_dispatched = 0u64;
let mut bulk_dispatched = 0u64;
for _ in 0..64 {
now += Duration::from_millis(1);
let SchedulerDecision::Dispatch(candidate) = fairness.next_decision(now) else {
break;
};
if candidate.frame.conn_id == 10 {
quickack_dispatched = quickack_dispatched.saturating_add(1);
} else if candidate.frame.conn_id == 20 {
bulk_dispatched = bulk_dispatched.saturating_add(1);
}
let _ = fairness.apply_dispatch_feedback(
candidate.frame.conn_id,
candidate,
DispatchFeedback::Routed,
now,
);
}
assert!(
quickack_dispatched > bulk_dispatched,
"quickack flow must receive higher dispatch rate with larger weight"
);
}
#[test]
fn fairness_pressure_hysteresis_prevents_instant_flapping() {
let mut now = Instant::now();
let mut cfg = WorkerFairnessConfig::default();
cfg.max_total_queued_bytes = 4096;
cfg.max_flow_queued_bytes = 4096;
cfg.pressure.evaluate_every_rounds = 1;
cfg.pressure.transition_hysteresis_rounds = 3;
cfg.pressure.queue_ratio_pressured_pct = 40;
cfg.pressure.queue_ratio_shedding_pct = 60;
cfg.pressure.queue_ratio_saturated_pct = 80;
let mut fairness = WorkerFairnessState::new(cfg, now);
for _ in 0..3 {
assert_eq!(
fairness.enqueue_data(9, 0, enqueue_payload(900), now),
AdmissionDecision::Admit
);
}
for _ in 0..2 {
now += Duration::from_millis(1);
let _ = fairness.next_decision(now);
}
assert_eq!(
fairness.pressure_state(),
PressureState::Normal,
"state must not flip before hysteresis confirmations"
);
}
#[test]
fn fairness_randomized_sequence_preserves_memory_bounds() {
let mut now = Instant::now();
let mut fairness = WorkerFairnessState::new(
WorkerFairnessConfig {
max_total_queued_bytes: 32 * 1024,
max_flow_queued_bytes: 4 * 1024,
..WorkerFairnessConfig::default()
},
now,
);
let mut seed = 0xC0FFEE_u64;
for _ in 0..4096 {
seed ^= seed << 7;
seed ^= seed >> 9;
seed ^= seed << 8;
let flow = (seed % 32) + 1;
let size = ((seed >> 8) % 512 + 64) as usize;
let _ = fairness.enqueue_data(flow, 0, enqueue_payload(size), now);
now += Duration::from_millis(1);
if let SchedulerDecision::Dispatch(candidate) = fairness.next_decision(now) {
let feedback = if seed & 0x1 == 0 {
DispatchFeedback::Routed
} else {
DispatchFeedback::QueueFull
};
let _ =
fairness.apply_dispatch_feedback(candidate.frame.conn_id, candidate, feedback, now);
}
let snapshot = fairness.snapshot();
let (standing_recomputed, backpressured_recomputed) =
fairness.debug_recompute_flow_counters(now);
assert!(snapshot.total_queued_bytes <= 32 * 1024);
assert_eq!(snapshot.standing_flows, standing_recomputed);
assert_eq!(snapshot.backpressured_flows, backpressured_recomputed);
assert!(fairness.debug_check_active_ring_consistency());
assert!(fairness.debug_max_deficit_bytes() <= 4 * 1024);
}
}

View File

@@ -104,6 +104,8 @@ async fn make_pool(
MeSocksKdfPolicy::default(),
general.me_writer_cmd_channel_capacity,
general.me_route_channel_capacity,
general.me_route_backpressure_enabled,
general.me_route_fairshare_enabled,
general.me_route_backpressure_base_timeout_ms,
general.me_route_backpressure_high_timeout_ms,
general.me_route_backpressure_high_watermark_pct,

View File

@@ -102,6 +102,8 @@ async fn make_pool(
MeSocksKdfPolicy::default(),
general.me_writer_cmd_channel_capacity,
general.me_route_channel_capacity,
general.me_route_backpressure_enabled,
general.me_route_fairshare_enabled,
general.me_route_backpressure_base_timeout_ms,
general.me_route_backpressure_high_timeout_ms,
general.me_route_backpressure_high_watermark_pct,

View File

@@ -97,6 +97,8 @@ async fn make_pool(me_pool_drain_threshold: u64) -> Arc<MePool> {
MeSocksKdfPolicy::default(),
general.me_writer_cmd_channel_capacity,
general.me_route_channel_capacity,
general.me_route_backpressure_enabled,
general.me_route_fairshare_enabled,
general.me_route_backpressure_base_timeout_ms,
general.me_route_backpressure_high_timeout_ms,
general.me_route_backpressure_high_watermark_pct,

View File

@@ -86,6 +86,8 @@ async fn make_pool() -> Arc<MePool> {
MeSocksKdfPolicy::default(),
general.me_writer_cmd_channel_capacity,
general.me_route_channel_capacity,
general.me_route_backpressure_enabled,
general.me_route_fairshare_enabled,
general.me_route_backpressure_base_timeout_ms,
general.me_route_backpressure_high_timeout_ms,
general.me_route_backpressure_high_watermark_pct,

View File

@@ -91,6 +91,8 @@ async fn make_pool() -> Arc<MePool> {
MeSocksKdfPolicy::default(),
general.me_writer_cmd_channel_capacity,
general.me_route_channel_capacity,
general.me_route_backpressure_enabled,
general.me_route_fairshare_enabled,
general.me_route_backpressure_base_timeout_ms,
general.me_route_backpressure_high_timeout_ms,
general.me_route_backpressure_high_watermark_pct,

View File

@@ -97,6 +97,8 @@ async fn make_pool() -> (Arc<MePool>, Arc<SecureRandom>) {
MeSocksKdfPolicy::default(),
general.me_writer_cmd_channel_capacity,
general.me_route_channel_capacity,
general.me_route_backpressure_enabled,
general.me_route_fairshare_enabled,
general.me_route_backpressure_base_timeout_ms,
general.me_route_backpressure_high_timeout_ms,
general.me_route_backpressure_high_watermark_pct,

View File

@@ -279,6 +279,12 @@ pub struct UpstreamApiSummarySnapshot {
pub shadowsocks_total: usize,
}
#[derive(Debug, Clone, Copy, Default)]
pub struct UpstreamApiHealthSummary {
pub configured_total: usize,
pub healthy_total: usize,
}
#[derive(Debug, Clone)]
pub struct UpstreamApiSnapshot {
pub summary: UpstreamApiSummarySnapshot,
@@ -444,6 +450,20 @@ impl UpstreamManager {
Some(UpstreamApiSnapshot { summary, upstreams })
}
pub async fn api_health_summary(&self) -> UpstreamApiHealthSummary {
let guard = self.upstreams.read().await;
let mut summary = UpstreamApiHealthSummary {
configured_total: guard.len(),
healthy_total: 0,
};
for upstream in guard.iter() {
if upstream.healthy {
summary.healthy_total += 1;
}
}
summary
}
fn describe_upstream(upstream_type: &UpstreamType) -> (UpstreamRouteKind, String) {
match upstream_type {
UpstreamType::Direct { .. } => (UpstreamRouteKind::Direct, "direct".to_string()),